© 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. 136880
    Prev
    Next
    INDEX
    Explanations

    advisor roles

    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
    סי
    0.62
     και
    0.59
    б
    0.53
    νου
    0.53
    נו
    0.52
     substitute
    0.52
     eram
    0.51
    Κ
    0.51
    је
    0.50
     district
    0.49
    POSITIVE LOGITS
    ักษณ์
    0.58
     Khab
    0.55
    なさ
    0.55
     Tohoku
    0.54
    IZATION
    0.54
    ization
    0.53
    etty
    0.53
     Ngày
    0.52
     इमरान
    0.52
     ഇക്കാര
    0.52
    Activations Density 0.000%

    No Known Activations