© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58288
    Prev
    Next
    INDEX
    Explanations

    colloquial language or colloquialisms

    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_11_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
    ب
    0.72
    كال
    0.68
    ات
    0.68
    كار
    0.66
    ين
    0.65
    ك
    0.61
    其他
    0.60
    "،
    0.60
    طه
    0.57
    ט
    0.57
    POSITIVE LOGITS
     noastră
    0.58
     пишу
    0.52
    meaning
    0.52
     Chancery
    0.52
    de
    0.51
    xy
    0.51
     vent
    0.51
     omit
    0.51
    ranger
    0.51
     brist
    0.51
    Activations Density 0.003%

    No Known Activations