© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13831
    Prev
    Next
    INDEX
    Explanations

    references to numerical data like statistics or dates

    oai_token-act-pair · gemini-2.0-flash

    Numeric data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Efq
    -0.75
     Majefty
    -0.62
     للاسماء
    -0.60
     perfons
    -0.60
     itſelf
    -0.57
     becauſe
    -0.56
    ]--;
    -0.56
     poffible
    -0.55
     purpoſe
    -0.55
     continúas
    -0.55
    POSITIVE LOGITS
     esternos
    0.60
    odo
    0.55
    <bos>
    0.53
    imageshack
    0.49
     Be
    0.49
    rade
    0.48
     estekak
    0.46
    Ấ
    0.45
     Berg
    0.44
    transQ
    0.44
    Activations Density 0.849%

    No Known Activations