© 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. 198580
    Prev
    Next
    INDEX
    Explanations

    vendor/composer paths

    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
    esas
    0.52
    圧力
    0.50
     amide
    0.50
     were
    0.49
     д
    0.49
     tyrant
    0.47
     antifer
    0.46
     MLB
    0.45
    oda
    0.44
     nende
    0.44
    POSITIVE LOGITS
    amız
    0.59
     паль
    0.58
     fått
    0.58
    နည်း
    0.56
    皮肤
    0.53
     nuove
    0.53
    ligi
    0.52
     त्वचा
    0.52
    A
    0.52
    ত্তর
    0.51
    Activations Density 0.000%

    No Known Activations