© 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. 13829
    Prev
    Next
    INDEX
    Explanations

    words pertaining to legal or regulatory cases and reports

    oai_token-act-pair · gemini-2.0-flash

    locations and situations

    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
     BorderRadius
    -0.59
    arschijnlijk
    -0.49
    ổi
    -0.48
    TabStop
    -0.45
    eficent
    -0.44
    xffffffff
    -0.44
    amation
    -0.43
    oxford
    -0.43
    lossians
    -0.43
    ksikon
    -0.43
    POSITIVE LOGITS
     where
    2.20
    where
    1.90
    Where
    1.69
     Where
    1.63
     donde
    1.54
     WHERE
    1.52
     où
    1.52
     где
    1.37
    WHERE
    1.34
    donde
    1.32
    Activations Density 4.188%

    No Known Activations