© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3719
    Prev
    Next
    INDEX
    Explanations

    都 + verb

    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_5_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
    饪
    0.78
    grimas
    0.71
     halftime
    0.65
    toolStrip
    0.64
    lep
    0.63
    漏
    0.62
     verr
    0.60
    날
    0.60
    นุ
    0.60
    倘
    0.60
    POSITIVE LOGITS
    ת
    0.89
    ა
    0.84
    beiter
    0.78
    recipes
    0.77
    ח
    0.76
    勻
    0.76
     ello
    0.76
    л
    0.75
    </table>
    0.74
     superficially
    0.73
    Activations Density 0.005%

    No Known Activations