© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13819
    Prev
    Next
    INDEX
    Explanations

    words that feature in restaurant reviews and food descriptions

    oai_token-act-pair · gemini-2.0-flash

    food dishes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AutoScaleMode
    -0.90
     HasFactory
    -0.84
     suivez
    -0.68
     avoient
    -0.68
     étoient
    -0.67
     auroit
    -0.67
     debout
    -0.66
     pouvoit
    -0.66
     étoit
    -0.63
     feroit
    -0.63
    POSITIVE LOGITS
     base
    0.52
     dég
    0.48
     dish
    0.47
     indulgence
    0.47
     spin
    0.45
     rehe
    0.45
     Zwischen
    0.44
    ẽ
    0.44
    []>
    0.43
    atalyst
    0.42
    Activations Density 4.468%

    No Known Activations