© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228522
    Prev
    Next
    INDEX
    Explanations

    -ato endings

    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
    h
    1.13
    و
    1.12
    ל
    1.02
    q
    0.96
    س
    0.95
    v
    0.94
    ts
    0.93
    ت
    0.93
    सँग
    0.92
    मधील
    0.91
    POSITIVE LOGITS
    اي
    0.95
    ิ่ง
    0.91
     බොහෝ
    0.86
     Được
    0.84
    ına
    0.84
    كي
    0.82
     ي
    0.79
    closes
    0.78
    يا
    0.78
     говорится
    0.78
    Activations Density 0.000%

    No Known Activations