© 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. 9708
    Prev
    Next
    INDEX
    Explanations

    XML tags including the "description" tag as well as the "name" tag, which suggests it is looking for metadata

    oai_token-act-pair · gemini-2.0-flash

    non-standard or unique identifiers

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

    Code and foreign language

    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
    ContentAlignment
    -0.60
    openzeppelin
    -0.60
    مقاله
    -0.56
    acterium
    -0.56
    enumii
    -0.56
    complexContent
    -0.56
    RetentionPolicy
    -0.55
    asiun
    -0.55
    ::~
    -0.54
    iedo
    -0.53
    POSITIVE LOGITS
     autorytatywna
    0.62
     فريبيس
    0.61
    ukone
    0.61
    ----</
    0.58
    Autoritní
    0.53
     AssemblyCulture
    0.53
    enterOuterAlt
    0.51
    Sucesor
    0.50
     >=",
    0.50
    ksikon
    0.48
    Activations Density 11.244%

    No Known Activations