© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227638
    Prev
    Next
    INDEX
    Explanations

    assembly `mov` instruction

    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
    ong
    1.40
    v
    1.20
    ang
    1.19
    ann
    1.02
    atan
    0.99
    ans
    0.98
    f
    0.94
    ont
    0.93
    em
    0.93
    aste
    0.92
    POSITIVE LOGITS
    ת
    1.45
    ب
    1.30
    ด
    1.21
    ו
    1.18
    ות
    1.15
    지
    1.13
    תו
    1.13
    ド
    1.12
    ก
    1.09
    ב
    1.09
    Activations Density 0.002%

    No Known Activations