© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212897
    Prev
    Next
    INDEX
    Explanations

    out of stock

    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_5_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
    ב
    2.00
    ل
    1.45
    л
    1.36
    ה
    1.31
    ب
    1.26
    ל
    1.18
    כ
    1.18
    ש
    1.15
    ne
    1.13
    ᐉ
    1.13
    POSITIVE LOGITS
    <0x80>
    1.44
     to
    1.14
    ↵
    1.09
    AR
    1.09
     (
    1.03
    ly
    1.01
    C
    0.98
     व
    0.95
    AL
    0.95
    iatric
    0.93
    Activations Density 0.000%

    No Known Activations