© 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. 246810
    Prev
    Next
    INDEX
    Explanations

    set of rules and specifications

    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
    setCellValue
    0.39
    夺
    0.39
    amel
    0.38
     Compl
    0.37
     Constit
    0.37
    แส
    0.36
     خوات
    0.36
     escritores
    0.35
     ssize
    0.35
    荼
    0.35
    POSITIVE LOGITS
    ﻝ
    0.43
    拱
    0.42
    Ү
    0.38
     combatir
    0.37
    실
    0.37
    hora
    0.36
    Altitude
    0.36
    Lon
    0.36
    
    0.36
     Patty
    0.35
    Activations Density 0.004%

    No Known Activations