© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12329
    Prev
    Next
    INDEX
    Explanations

    a mix of discourse markers and terminology related to family, percentages, statistical studies and the relationship between things.

    oai_token-act-pair · gemini-2.0-flash

    both

    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
    both
    -3.08
    Both
    -3.06
     both
    -3.05
     Both
    -3.02
    BOTH
    -2.73
     BOTH
    -2.69
     ambos
    -2.39
    Ambos
    -2.36
     entrambi
    -2.36
     begge
    -2.33
    POSITIVE LOGITS
    ">//
    0.66
    URLException
    0.57
     disambiguazione
    0.52
    참고
    0.49
    ?,?,
    0.48
     ulaş
    0.46
    âmetros
    0.46
    <?
    0.45
     нат
    0.45
    utilisons
    0.43
    Activations Density 7.902%

    No Known Activations