© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7988
    Prev
    Next
    INDEX
    Explanations

    *

    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
    maßen
    3.06
    SCAPE
    2.81
     таки
    2.80
    朓
    2.74
    воен
    2.73
    甭
    2.73
    вро
    2.70
    pull
    2.65
    cieron
    2.61
    ೂರ್ಯ
    2.58
    POSITIVE LOGITS
    ことに
    2.71
    ことを
    2.68
    levard
    2.66
    signUp
    2.63
    ົວ
    2.61
    eils
    2.55
    िक
    2.54
    ್
    2.52
    🅔
    2.48
     unul
    2.48
    Activations Density 0.471%

    No Known Activations