© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31495
    Prev
    Next
    INDEX
    Explanations

    academic citations author year

    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_31_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
     тео
    0.39
     unre
    0.39
     theorems
    0.39
     jugador
    0.38
    لاعب
    0.37
     раст
    0.36
    мат
    0.36
    莠
    0.35
     initialise
    0.35
     сорта
    0.35
    POSITIVE LOGITS
    roadmap
    0.37
    أم
    0.36
    gives
    0.36
    아가
    0.35
    steuerung
    0.35
    कह
    0.35
    izons
    0.34
     Shelter
    0.34
    ackel
    0.34
    facing
    0.34
    Activations Density 0.001%

    No Known Activations