© 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. 141236
    Prev
    Next
    INDEX
    Explanations

    Device Manager or system headers

    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
    ਾ
    0.14
    鎚
    0.14
    猗
    0.14
    كي
    0.13
    ших
    0.13
    かけた
    0.13
     doby
    0.13
    ண
    0.13
    餒
    0.13
    גל
    0.13
    POSITIVE LOGITS
    ifications
    0.14
    chi
    0.14
    .<
    0.13
    OL
    0.13
     through
    0.13
     वहीं
    0.13
     संशोधन
    0.13
     thấm
    0.13
    OutOf
    0.13
     vitth
    0.12
    Activations Density 0.003%

    No Known Activations