© 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. 236974
    Prev
    Next
    INDEX
    Explanations

    planets

    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
    iego
    0.47
    pol
    0.38
    ieux
    0.37
    追踪
    0.36
     E
    0.36
    ercase
    0.35
    ȟ
    0.35
     S
    0.35
     precedence
    0.35
    ggi
    0.35
    POSITIVE LOGITS
     Tee
    0.40
     poached
    0.40
     tees
    0.38
     aphids
    0.38
    isce
    0.37
     Tyre
    0.37
     Vos
    0.37
     Halsey
    0.37
     exerc
    0.37
    锈
    0.37
    Activations Density 0.001%

    No Known Activations