© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36389
    Prev
    Next
    INDEX
    Explanations

    list item

    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
    ي
    1.31
    ח
    0.82
    나
    0.81
    v
    0.77
    ک
    0.75
    i
    0.74
    ط
    0.74
    տ
    0.74
    其他
    0.73
    تو
    0.71
    POSITIVE LOGITS
    ía
    0.65
     penchant
    0.61
     breadth
    0.59
     bespoke
    0.58
     parametr
    0.58
     forgo
    0.58
     i
    0.56
     baseline
    0.56
     café
    0.56
     battling
    0.56
    Activations Density 0.002%

    No Known Activations