© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204278
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     क्विंट
    0.52
    姹
    0.45
    𝔪
    0.45
    studio
    0.44
    ären
    0.44
    പരമായ
    0.44
    🎻
    0.43
    pins
    0.43
     Balfour
    0.43
    溅
    0.43
    POSITIVE LOGITS
     metabol
    0.44
     compute
    0.41
     carbohydrate
    0.40
     became
    0.40
     reim
    0.39
     rotated
    0.39
     validate
    0.38
     PE
    0.38
     aforementioned
    0.38
    фе
    0.37
    Activations Density 0.000%

    No Known Activations