© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54055
    Prev
    Next
    INDEX
    Explanations

    places and settings

    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_55_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
     էին
    0.40
     erano
    0.39
    রাগ
    0.39
     Agree
    0.39
     formulas
    0.38
     ENEM
    0.38
    炎
    0.38
    态度
    0.37
    빴
    0.37
     prompts
    0.37
    POSITIVE LOGITS
    Markets
    0.46
    Market
    0.39
     Markets
    0.39
    的市场
    0.38
    Throughout
    0.38
    Digit
    0.37
    싣
    0.37
     seizing
    0.37
     يستخدم
    0.37
    {'
    0.36
    Activations Density 0.009%

    No Known Activations