© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120988
    Prev
    Next
    INDEX
    Explanations

    login, Withdraw, Builder, Sig, 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_27_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
     Dependent
    0.34
     Depends
    0.33
     Puede
    0.33
     Gotham
    0.31
         
    0.30
     อาจ
    0.30
     Pais
    0.29
    誌
    0.29
     Zeitschrift
    0.29
     cone
    0.28
    POSITIVE LOGITS
     plages
    0.34
    posaż
    0.33
    समझ
    0.32
     jakości
    0.32
     механи
    0.31
    হো
    0.31
     amplo
    0.31
    renown
    0.31
    贖
    0.31
    ما
    0.30
    Activations Density 0.001%

    No Known Activations