© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8259
    Prev
    Next
    INDEX
    Explanations

    words associated with food reviews

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms and concepts

    np_token-act-pair-logits · gpt-4o-mini

    flavor and taste

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     betweenstory
    -0.63
    AccessorTable
    -0.45
     lui
    -0.45
    Begriffsklä
    -0.43
     históricas
    -0.43
    TagMode
    -0.43
    toMatch
    -0.43
    IBOutlet
    -0.42
     chant
    -0.42
    átu
    -0.42
    POSITIVE LOGITS
    UnitTesting
    0.60
     calendriers
    0.58
    ContentAsync
    0.57
    localctx
    0.56
     requestCode
    0.55
    fulness
    0.55
    endregion
    0.53
    kloped
    0.51
    ArgsConstructor
    0.51
     Profile
    0.51
    Activations Density 1.807%

    No Known Activations