© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221683
    Prev
    Next
    INDEX
    Explanations

    name and nombre

    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_10_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
    0.34
    c
    0.32
    ছিল
    0.29
     Its
    0.28
     In
    0.28
    ется
    0.28
    и
    0.28
    ك
    0.27
     in
    0.27
     were
    0.27
    POSITIVE LOGITS
     성능
    0.27
    ANS
    0.27
    ANG
    0.27
    ONG
    0.26
    問題を
    0.26
    who
    0.26
    AG
    0.25
    ONT
    0.25
     clotting
    0.25
    ENT
    0.25
    Activations Density 0.007%

    No Known Activations