© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62380
    Prev
    Next
    INDEX
    Explanations

    virtue and flourishing

    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
    İ
    0.54
    Ş
    0.54
    ६
    0.53
     Railway
    0.52
     Für
    0.51
    מו
    0.50
    Für
    0.50
    ३
    0.50
     zu
    0.50
    க்கு
    0.49
    POSITIVE LOGITS
     medallions
    0.64
     tints
    0.58
     клиента
    0.56
     cooldown
    0.56
     fillets
    0.56
     attho
    0.55
    ա
    0.54
     ingred
    0.54
     coupons
    0.53
    즈
    0.53
    Activations Density 0.047%

    No Known Activations