© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199871
    Prev
    Next
    INDEX
    Explanations

    possible actions or outcomes

    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
    (
    0.34
    д
    0.33
    스
    0.30
    ある
    0.30
    마다
    0.30
    +
    0.30
    ない
    0.29
     강조
    0.29
    sur
    0.28
    ਤ
    0.27
    POSITIVE LOGITS
    is
    0.37
    i
    0.35
    il
    0.34
    ي
    0.33
    െ
    0.33
    يلا
    0.32
     دوسری
    0.31
    en
    0.31
     escánd
    0.30
    EN
    0.30
    Activations Density 0.003%

    No Known Activations