© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14137
    Prev
    Next
    INDEX
    Explanations

    words related to rules, facts, and truth

    oai_token-act-pair · gemini-2.0-flash

    "to be" and "to do"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    kä
    -0.51
     reik
    -0.45
    섭
    -0.44
    дзе
    -0.44
     linge
    -0.43
    ti
    -0.42
     geodesic
    -0.41
     Cov
    -0.41
    لي
    -0.40
    álat
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.89
     ModelExpression
    0.84
     onAnimation
    0.78
    SequentialGroup
    0.77
    ⓧ
    0.75
     مشين
    0.73
    UserScript
    0.72
    IndentedString
    0.71
     GenerationType
    0.71
     AssemblyCompany
    0.70
    Activations Density 11.431%

    No Known Activations