© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12220
    Prev
    Next
    INDEX
    Explanations

    the word "success" and words associated with growth or evaluation

    oai_token-act-pair · gemini-2.0-flash

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -0.94
    polation
    -0.94
     Anſ
    -0.86
    NOUNC
    -0.85
     Theſe
    -0.85
     becauſe
    -0.84
    "]).
    -0.83
     IBRARY
    -0.83
     pleaſure
    -0.82
    BibitemShut
    -0.82
    POSITIVE LOGITS
    IntoConstraints
    0.80
    MigrationBuilder
    0.76
    RenderAtEndOf
    0.69
     metav
    0.66
    as
    0.63
     GenerationType
    0.63
    AxisAlignment
    0.61
    .
    0.60
    same
    0.60
    er
    0.59
    Activations Density 1.364%

    No Known Activations