© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10115
    Prev
    Next
    INDEX
    Explanations

    fragments of text describing a specific fictional skill, item, or entity named "Kyutama" and related concepts within a narrative context, often involving character actions and events.

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    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
    WriteTagHelper
    -0.70
     NUKAT
    -0.68
    GraphicsUnit
    -0.60
    DoubleQuotes
    -0.57
    aarrggbb
    -0.55
     Normdatei
    -0.54
    NUMX
    -0.54
     saites
    -0.52
    MERCE
    -0.52
    rairie
    -0.52
    POSITIVE LOGITS
    Roar
    0.47
    魔
    0.41
    v
    0.41
    Hulk
    0.39
     pregă
    0.38
    te
    0.38
     militares
    0.38
    ⓧ
    0.38
    }]);
    0.38
     pirata
    0.37
    Activations Density 18.882%

    No Known Activations