© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14242
    Prev
    Next
    INDEX
    Explanations

    words that describe something being assessed or evaluated

    oai_token-act-pair · gemini-2.0-flash

    approved

    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
     Audiodateien
    -0.69
    
    -0.68
    RegressionTest
    -0.63
    énario
    -0.60
     للمعارف
    -0.60
     beginnetje
    -0.59
    wartet
    -0.59
    abestanden
    -0.58
    ponses
    -0.57
    toko
    -0.56
    POSITIVE LOGITS
    CloseOperation
    0.55
    rrggbb
    0.51
    <?=
    0.50
     Wikispecies
    0.50
    COUVER
    0.49
    NameInMap
    0.49
    Билгалдахарш
    0.48
    ByteBuf
    0.47
     Exactos
    0.46
     Sitten
    0.44
    Activations Density 4.405%

    No Known Activations