© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3795
    Prev
    Next
    INDEX
    Explanations

    words related to member satisfaction or customer retention

    oai_token-act-pair · gemini-2.0-flash

    business concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    таратура
    -0.53
    geries
    -0.49
    quam
    -0.49
    ogh
    -0.49
    shire
    -0.47
    EREF
    -0.47
    ättern
    -0.47
    culi
    -0.46
    TypeDefinition
    -0.45
    elm
    -0.45
    POSITIVE LOGITS
    featureID
    0.66
     виправивши
    0.62
    TypedDataSet
    0.61
    AnchorStyles
    0.60
    UpInside
    0.60
    ✭✭
    0.59
    enterOuterAlt
    0.57
     endforeach
    0.57
     Chriftian
    0.57
    setof
    0.56
    Activations Density 1.174%

    No Known Activations