© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5038
    Prev
    Next
    INDEX
    Explanations

    voice properties like name and id

    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_39_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
    ppo
    0.44
    ̣c
    0.42
    otion
    0.42
    ṯ
    0.41
     memper
    0.40
     kus
    0.38
    esch
    0.38
     نکل
    0.38
    quiz
    0.38
    orious
    0.38
    POSITIVE LOGITS
     Aber
    0.39
    Constr
    0.39
     Subst
    0.39
    子里
    0.38
    闸
    0.38
     га
    0.37
    スタンダード
    0.37
     incarn
    0.36
     exchanger
    0.36
     Screenshots
    0.36
    Activations Density 0.002%

    No Known Activations