© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1613
    Prev
    Next
    INDEX
    Explanations

    the possessive "'ll" and words related to health risks, or other abstract risks

    oai_token-act-pair · gemini-2.0-flash

    Random mixed internet data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    SourceChecksum
    -0.88
    MigrationBuilder
    -0.60
    TypedDataSet
    -0.59
    fjspx
    -0.59
    LookAnd
    -0.57
    Portale
    -0.57
     للمعارف
    -0.55
    SharedCtor
    -0.54
    EndInit
    -0.54
     []).
    -0.52
    POSITIVE LOGITS
    SBATCH
    0.65
     wikipagina
    0.58
    CastException
    0.57
    Hauptartikel
    0.54
     RIPRODUZIONE
    0.53
     KeyError
    0.52
    ROID
    0.51
    Beijinhos
    0.50
     ainfi
    0.50
     nawr
    0.49
    Activations Density 0.034%

    No Known Activations