© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206725
    Prev
    Next
    INDEX
    Explanations

    sql comments

    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_10_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
     $
    0.95
     (
    0.86
    ed
    0.67
    、
    0.66
     {
    0.65
    ôtel
    0.62
     can
    0.61
    ~$
    0.61
    नातील
    0.61
     BONUS
    0.61
    POSITIVE LOGITS
    the
    0.78
    ว่า
    0.75
    ่
    0.71
    𝙨
    0.66
    sthe
    0.66
    りたい
    0.64
    rsquo
    0.64
    questions
    0.63
    same
    0.62
    뚠
    0.62
    Activations Density 0.000%

    No Known Activations