© 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. 6653
    Prev
    Next
    INDEX
    Explanations

    a bizarre collection of alphanumeric, French, API code, statistics, and medical terms.

    oai_token-act-pair · gemini-2.0-flash

    afe

    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
    e
    -0.72
    ctomy
    -0.69
    ٔ
    -0.67
    eeee
    -0.66
    eeeee
    -0.65
    eee
    -0.64
    eeeeeeee
    -0.64
    eeeeee
    -0.59
    ً
    -0.58
     ای
    -0.57
    POSITIVE LOGITS
    ness
    1.47
    을
    0.94
    nya
    0.89
    은
    0.88
    으로
    0.88
    n
    0.79
    NESS
    0.79
    ned
    0.72
    ship
    0.72
    과
    0.71
    Activations Density 10.267%

    No Known Activations