© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15087
    Prev
    Next
    INDEX
    Explanations

    npm errors

    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
    distanceArray
    0.40
    $+
    0.39
     :+:
    0.39
     oğ
    0.39
    Outfit
    0.38
    ActivityCompat
    0.38
     ওয়
    0.38
    𒉡
    0.37
    DistanceFrom
    0.37
     منط
    0.37
    POSITIVE LOGITS
     actions
    0.47
     transaction
    0.42
     Interaction
    0.42
     interaction
    0.40
     Great
    0.40
     action
    0.39
     Internal
    0.38
     Transaction
    0.38
    完了
    0.38
    interaction
    0.37
    Activations Density 0.004%

    No Known Activations