© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10876
    Prev
    Next
    INDEX
    Explanations

    code snippets in HTML and Angular.

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ProtoMessage
    -0.57
     estekak
    -0.54
     GenerationType
    -0.53
    Pratique
    -0.49
     Kalyan
    -0.49
    semibold
    -0.48
     Presence
    -0.47
     समीक्षाओं
    -0.47
    omal
    -0.47
    Toponymie
    -0.47
    POSITIVE LOGITS
     invokingState
    0.56
    EndProject
    0.52
    pezi
    0.50
    PhysRev
    0.50
    netinet
    0.47
    endpush
    0.46
     skimage
    0.45
     creatinine
    0.45
    istió
    0.44
    providedIn
    0.43
    Activations Density 0.160%

    No Known Activations