© 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. 2682
    Prev
    Next
    INDEX
    Explanations

    technical software related terminology

    oai_token-act-pair · gemini-2.0-flash

    words relating to integration and connection

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

    code and programming

    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
     насељу
    -0.82
     صوتيه
    -0.81
    ValueStyle
    -0.75
     surla
    -0.73
     Administrativna
    -0.70
    IndentedString
    -0.65
     wireType
    -0.63
    setPointSize
    -0.63
    Geplaatst
    -0.63
    Życiorys
    -0.61
    POSITIVE LOGITS
    BindingResult
    0.59
     baked
    0.51
     inter
    0.50
    raszamy
    0.49
     deeply
    0.46
    ratulations
    0.45
    vener
    0.44
     integrated
    0.44
     integrates
    0.44
     pinulongan
    0.44
    Activations Density 5.773%

    No Known Activations