© 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. 12277
    Prev
    Next
    INDEX
    Explanations

    C++ template syntax

    oai_token-act-pair · gemini-2.0-flash

    <

    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
    <
    -1.31
     <
    -0.77
    }<
    -0.55
    <\
    -0.54
    )<
    -0.54
    <!
    -0.53
    ?<
    -0.52
    !<
    -0.52
    <$
    -0.51
    ]<
    -0.50
    POSITIVE LOGITS
    matchCondition
    0.87
     ModelExpression
    0.77
     ostavi
    0.75
     AssemblyProduct
    0.73
    GOTREF
    0.70
    তথ্যসূত্র
    0.70
    IVEREF
    0.66
    OGND
    0.66
    \{\\
    0.65
    ագրություններ
    0.64
    Activations Density 1.485%

    No Known Activations