© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38194
    Prev
    Next
    INDEX
    Explanations

    words ending in -able, -ible, -ive, -ment, -act

    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
    ك
    0.86
    c
    0.82
    ف
    0.76
    ל
    0.74
    ב
    0.72
    ட
    0.70
    مل
    0.64
    ص
    0.64
     in
    0.61
    in
    0.61
    POSITIVE LOGITS
    ing
    0.96
    ة
    0.78
    itous
    0.75
    us
    0.74
    কেও
    0.74
    MUX
    0.73
    jna
    0.72
    ají
    0.71
    jne
    0.71
     compart
    0.69
    Activations Density 0.016%

    No Known Activations