© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16001
    Prev
    Next
    INDEX
    Explanations

    sports-related terminology and team names

    oai_token-act-pair · gemini-2.0-flash

    physical actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    sizeCache
    -0.85
    tvguidetime
    -0.78
    сылкі
    -0.76
     שוליים
    -0.76
    MessageOf
    -0.74
     חיצוניים
    -0.74
     Италијани
    -0.73
    msgTypes
    -0.73
    CodedInputStream
    -0.66
    Välislingid
    -0.65
    POSITIVE LOGITS
     rimu
    0.49
     hawa
    0.47
     claves
    0.46
     deep
    0.46
    TITUDE
    0.44
    fromCharCode
    0.44
    deep
    0.43
     Champion
    0.43
    ArgsConstructor
    0.42
    gman
    0.42
    Activations Density 2.707%

    No Known Activations