© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34835
    Prev
    Next
    INDEX
    Explanations

    relevantappropriateknown

    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_7_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
    in
    0.36
     obu
    0.35
    es
    0.33
    ม
    0.33
     innych
    0.31
    스
    0.31
    Ti
    0.31
    म
    0.30
    および
    0.29
    න්ට
    0.29
    POSITIVE LOGITS
    nements
    0.32
    +
    0.31
     합니다
    0.28
    𝙫
    0.27
    <0x81>
    0.27
    riculum
    0.27
    "，
    0.27
    ក់
    0.26
    "="
    0.26
     ت
    0.25
    Activations Density 0.069%

    No Known Activations