© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141476
    Prev
    Next
    INDEX
    Explanations

    various Slavic prefixes/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_12_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
    B
    0.98
    D
    0.80
    P
    0.74
    G
    0.71
    L
    0.69
    ду
    0.68
    T
    0.67
    তা
    0.64
    BUT
    0.63
     inú
    0.62
    POSITIVE LOGITS
    к
    0.93
    '
    0.76
     to
    0.72
    л
    0.69
    д
    0.68
    er
    0.68
     critic
    0.68
    6
    0.68
    اً
    0.67
    в
    0.61
    Activations Density 0.001%

    No Known Activations