© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7695
    Prev
    Next
    INDEX
    Explanations

    the keyword "const" and sometimes highlights a choice between alternatives

    oai_token-act-pair · gemini-2.0-flash

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    MigrationBuilder
    -1.13
    webElementXpaths
    -1.06
     présidenti
    -1.03
     feroit
    -1.02
     duquel
    -1.02
     hiér
    -1.02
     élas
    -1.01
     fédé
    -1.01
     définiti
    -1.01
     indígen
    -0.99
    POSITIVE LOGITS
     and
    0.88
     of
    0.63
     (
    0.60
     “
    0.58
     in
    0.57
     or
    0.57
    ,
    0.53
     The
    0.53
    com
    0.52
     ef
    0.52
    Activations Density 1.356%

    No Known Activations