© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12058
    Prev
    Next
    INDEX
    Explanations

    code documentation tags like @param, @return, /// and pragmas

    oai_token-act-pair · gemini-2.0-flash

    "///" and "*"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    RTLD
    -0.56
    localScale
    -0.55
     AssemblyProduct
    -0.54
    NewGuid
    -0.53
    styleable
    -0.51
    tokenId
    -0.50
    clientY
    -0.50
    TypedDataSet
    -0.50
    Gweler
    -0.50
    RIL
    -0.48
    POSITIVE LOGITS
    Rhestr
    0.63
    Oneof
    0.60
    RenderAtEndOf
    0.58
    цездатний
    0.55
    แรง
    0.55
     discussione
    0.53
    noopener
    0.52
    actéristique
    0.51
     känd
    0.51
    ˈ
    0.51
    Activations Density 0.553%

    No Known Activations