© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5523
    Prev
    Next
    INDEX
    Explanations

    crucial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pseudo
    1.38
     таки
    1.37
    其
    1.25
     Tired
    1.15
    깐
    1.15
    ographic
    1.15
     Guer
    1.15
    TableCell
    1.14
    ശാസ്ത്ര
    1.13
    $>
    1.12
    POSITIVE LOGITS
    le
    1.30
    ا
    1.13
    𝑎
    1.09
    a
    1.04
    lt
    1.03
    ا۔
    1.02
    siniz
    1.01
    اا
    1.01
     extingu
    1.00
    tte
    0.99
    Activations Density 0.524%

    No Known Activations