© 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. 89531
    Prev
    Next
    INDEX
    Explanations

    declension, pardon, or Russian 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_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
     to
    0.50
     Ti
    0.47
    ia
    0.45
     Nath
    0.45
    ↵
    0.44
     н
    0.44
    ᛁ
    0.44
    RAIN
    0.43
     другим
    0.43
     definizione
    0.43
    POSITIVE LOGITS
    gano
    0.61
    kipun
    0.57
    jangan
    0.55
    aunque
    0.55
    akang
    0.54
    怎样的
    0.54
    야
    0.54
    க்கிழ
    0.54
     wardrobe
    0.54
     archipelago
    0.52
    Activations Density 0.008%

    No Known Activations