© 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. 1127
    Prev
    Next
    INDEX
    Explanations

    the acronym "Kyutama" and nearby words describing it.

    oai_token-act-pair · gemini-2.0-flash

    Kyutama series

    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
    Демографія
    -0.94
    WebVitals
    -0.86
     Мексичка
    -0.74
    NewUrlParser
    -0.70
    exitRule
    -0.69
    EndContext
    -0.64
    AndEndTag
    -0.63
    zzleHttp
    -0.61
     صوتيه
    -0.59
    MigrationBuilder
    -0.57
    POSITIVE LOGITS
    portál
    0.52
     Gotta
    0.47
     Bolt
    0.47
    Bolt
    0.45
     bomb
    0.44
     jaws
    0.44
     gauntlet
    0.43
    BOL
    0.43
    flare
    0.43
    nado
    0.42
    Activations Density 8.720%

    No Known Activations