© 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-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56578
    Prev
    Next
    INDEX
    Explanations

    noticeably different or significant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
     ಸಾಕಷ್ಟು
    0.60
    1
    0.59
     μέχρι
    0.57
    FAF
    0.57
    Ί
    0.55
    '
    0.53
    gono
    0.51
    ymmetrical
    0.51
    4
    0.51
     jalan
    0.49
    POSITIVE LOGITS
    وڈ
    0.56
    iential
    0.55
    ='.
    0.54
    œ
    0.54
    و
    0.53
     razvoj
    0.52
    كور
    0.50
    icheskij
    0.50
    タ
    0.50
    디어
    0.49
    Activations Density 0.002%

    No Known Activations