© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195152
    Prev
    Next
    INDEX
    Explanations

    gaming and tech events

    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_50_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
     Panzer
    0.41
     Panther
    0.40
     Lever
    0.39
     Nein
    0.38
     Fan
    0.38
     Point
    0.38
     Partner
    0.38
    惮
    0.38
     cont
    0.37
    鳗
    0.37
    POSITIVE LOGITS
    戦争
    0.41
    情報の
    0.41
    🍊
    0.41
     Woj
    0.41
    ℙ
    0.39
    Bloomberg
    0.39
    kaj
    0.38
    கொ
    0.38
    harm
    0.37
    Scrim
    0.37
    Activations Density 0.000%

    No Known Activations