© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11595
    Prev
    Next
    INDEX
    Explanations

    technical writing about scientific topics and legal or financial conditions

    oai_token-act-pair · gemini-2.0-flash

    conditions or circumstances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ########.
    -0.86
    paravant
    -0.78
     للمعارف
    -0.75
     Administrativna
    -0.69
    IVEREF
    -0.66
    expandindo
    -0.66
    iterranée
    -0.66
     familiare
    -0.66
    tagHelperRunner
    -0.66
    tymologie
    -0.66
    POSITIVE LOGITS
    Portály
    0.50
    esModule
    0.50
    <bos>
    0.45
    ccin
    0.43
     Weeknd
    0.42
    sequelize
    0.42
    volley
    0.42
     <<<<<<<<<<<<<<
    0.41
    XDECREF
    0.41
    ----------------
    0.41
    Activations Density 3.938%

    No Known Activations