© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9199
    Prev
    Next
    INDEX
    Explanations

    measurement units and related scientific abbreviations

    oai_token-act-pair · gemini-2.0-flash

    technical measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    rungsseite
    -0.95
    ThroughAttribute
    -0.68
    principalColumn
    -0.68
     ويكيميديا
    -0.68
    ModelSerializer
    -0.67
     دیکھیے
    -0.66
    findpost
    -0.65
     ویکی‌آمباردا
    -0.65
    }))
    -0.65
     Distance
    -0.64
    POSITIVE LOGITS
    Điều
    0.52
    σκε
    0.46
    RenderAtEndOf
    0.45
     Betracht
    0.45
    ập
    0.45
     sério
    0.45
    SourceChecksum
    0.44
     conserv
    0.44
     kelp
    0.44
    Trọng
    0.43
    Activations Density 1.699%

    No Known Activations