© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146338
    Prev
    Next
    INDEX
    Explanations

    games and **checkers**

    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_18_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
     de
    0.57
     Chalmers
    0.55
    6
    0.50
     Carol
    0.48
     Dorothe
    0.48
    比
    0.48
    1
    0.47
     contender
    0.46
    8
    0.45
     Dolomites
    0.45
    POSITIVE LOGITS
    揶
    0.53
    rq
    0.50
    jenih
    0.49
     연료
    0.48
    颞
    0.48
    ⍵
    0.48
    realpath
    0.48
    swadian
    0.48
     αφού
    0.48
     وہاں
    0.47
    Activations Density 0.000%

    No Known Activations