© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2375
    Prev
    Next
    INDEX
    Explanations

    text related to legal proceedings and news broadcasting

    oai_token-act-pair · gemini-2.0-flash

    terms related to ongoing or continuous states

    np_token-act-pair-logits · gpt-4o-mini

    constant, continuous

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.80
     scolaires
    -0.75
     JpaRepository
    -0.72
     nahilalakip
    -0.68
    SequentialGroup
    -0.67
    SceneManagement
    -0.65
    setVerticalGroup
    -0.64
     extérieurs
    -0.62
     religieuses
    -0.60
     aikaa
    -0.60
    POSITIVE LOGITS
     constant
    1.79
     continuous
    1.59
    constant
    1.47
     Constant
    1.44
     constantly
    1.43
     permanent
    1.40
     continuously
    1.39
     Continuous
    1.37
    Constant
    1.36
    continuous
    1.35
    Activations Density 2.967%

    No Known Activations