© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6429
    Prev
    Next
    INDEX
    Explanations

    Japanese language used in a software development context

    oai_token-act-pair · gemini-2.0-flash

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Monfieur
    -0.93
     BoxDecoration
    -0.90
     themſelves
    -0.88
     ſeveral
    -0.82
     ſmall
    -0.81
     greateſt
    -0.76
     reaſon
    -0.76
     Theſe
    -0.75
     leaſt
    -0.73
     theſe
    -0.73
    POSITIVE LOGITS
     Roskov
    0.59
    ként
    0.46
     Reverso
    0.46
    を
    0.46
    lež
    0.43
    를
    0.43
    Demografie
    0.41
    windowFixed
    0.41
    ،
    0.39
    setupUi
    0.39
    Activations Density 0.505%

    No Known Activations