© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108649
    Prev
    Next
    INDEX
    Explanations

    restriction and challenges

    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_1_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
    </h2>
    1.23
    ک
    1.23
     It
    1.11
    <0x0D>
    1.07
     that
    1.03
    ip
    1.02
     on
    0.98
     with
    0.96
    ong
    0.96
    ین
    0.94
    POSITIVE LOGITS
    ↵↵
    1.28
    ك
    1.16
     Más
    1.00
    يريا
    0.98
    دين
    0.96
    ка
    0.95
    利的
    0.93
    د
    0.93
     શું
    0.92
    كين
    0.92
    Activations Density 0.007%

    No Known Activations