© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215204
    Prev
    Next
    INDEX
    Explanations

    pro- prefixes and words starting with "far"

    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_31_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
    🏍
    0.37
    descriptions
    0.36
     jenis
    0.36
     tipo
    0.34
     motionProxy
    0.33
     anaknya
    0.33
     forment
    0.32
     इंट्रोडक्शन
    0.32
    穷
    0.32
    spirited
    0.32
    POSITIVE LOGITS
     Hak
    0.35
     ordinance
    0.34
     Un
    0.34
     hak
    0.33
     buck
    0.33
     Pre
    0.32
    FERRED
    0.32
    id
    0.32
    dk
    0.32
    issance
    0.31
    Activations Density 0.000%

    No Known Activations