© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247035
    Prev
    Next
    INDEX
    Explanations

    $_ POST

    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_40_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
     drops
    0.42
     Dishes
    0.40
     drop
    0.40
     ໜ
    0.38
     Drops
    0.38
     Drop
    0.38
    ularity
    0.38
    Drops
    0.37
    வற்ற
    0.37
    redient
    0.37
    POSITIVE LOGITS
     Counselor
    0.39
    াজের
    0.39
    ງານ
    0.38
    SV
    0.38
    QH
    0.37
    突
    0.36
    FBSDKGraph
    0.36
     Jérôme
    0.36
    ネイル
    0.36
    Counsel
    0.36
    Activations Density 0.000%

    No Known Activations