© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229617
    Prev
    Next
    INDEX
    Explanations

    Newegg

    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_6_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
    দের
    1.16
    ات
    1.14
    ak
    1.09
    as
    1.00
    ’
    1.00
    كس
    1.00
    ↵
    0.99
    يه
    0.99
    ى
    0.98
    ك
    0.97
    POSITIVE LOGITS
    (
    1.11
    (−
    0.98
     abrasion
    0.91
    الی
    0.89
     aves
    0.89
     exogenous
    0.87
    (,
    0.86
    ({\
    0.85
     паль
    0.85
     incontinence
    0.85
    Activations Density 0.000%

    No Known Activations