© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85472
    Prev
    Next
    INDEX
    Explanations

    Hungarian words and suffixes

    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_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
    '};
    0.79
    ي
    0.74
    '}}
    0.69
    Quantidade
    0.68
    LIMITED
    0.68
    حي
    0.67
     tyto
    0.66
    К
    0.66
    L
    0.65
    فري
    0.64
    POSITIVE LOGITS
    ación
    0.73
    in
    0.71
     at
    0.64
     the
    0.64
    𝗯
    0.64
    ない
    0.63
     incandescent
    0.61
    ia
    0.61
     with
    0.60
     activating
    0.60
    Activations Density 0.000%

    No Known Activations