© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236932
    Prev
    Next
    INDEX
    Explanations

    to be

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    cooler
    0.41
    cool
    0.41
    COOL
    0.38
     Tear
    0.38
    Cool
    0.38
     tearing
    0.38
    daar
    0.38
    쿨
    0.38
     COOL
    0.37
    丿
    0.37
    POSITIVE LOGITS
     facets
    0.41
    enders
    0.39
     strategies
    0.39
     Beaver
    0.38
     떨어
    0.38
     Strategies
    0.37
    QD
    0.37
     MacDonald
    0.36
     Q
    0.36
    盛り
    0.36
    Activations Density 0.005%

    No Known Activations