© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124292
    Prev
    Next
    INDEX
    Explanations

    categorizing likelihood

    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
    ar
    0.66
    ER
    0.58
    {
    0.57
    TER
    0.55
    am
    0.54
    arh
    0.54
    ఎఫ్
    0.54
    DD
    0.53
    ává
    0.53
    ávat
    0.52
    POSITIVE LOGITS
     (
    0.57
    不
    0.55
    ה
    0.55
     progen
    0.55
    ין
    0.54
    0.53
     convenc
    0.53
     concatenated
    0.53
    j
    0.53
     মুজিবের
    0.52
    Activations Density 0.000%

    No Known Activations