© 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. 46628
    Prev
    Next
    INDEX
    Explanations

    other, another

    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
     The
    0.30
     ACLU
    0.25
     Charlie
    0.25
     U
    0.25
     As
    0.25
     Mafia
    0.25
     Five
    0.24
    ный
    0.24
     NYC
    0.24
     Don
    0.24
    POSITIVE LOGITS
     perfecto
    0.26
    ।
    0.23
     proporcion
    0.22
     corrugated
    0.22
    BIN
    0.22
     meagre
    0.22
     ज
    0.21
     طاقت
    0.21
     జరిగ
    0.21
    .//
    0.21
    Activations Density 0.006%

    No Known Activations