© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176389
    Prev
    Next
    INDEX
    Explanations

    If

    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_24_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
     depuis
    0.36
    ライ
    0.35
    大きな
    0.35
     وا
    0.34
     শাসনের
    0.34
     아닌
    0.33
    Пі
    0.33
    ﯼ
    0.33
     sejak
    0.33
    Depuis
    0.32
    POSITIVE LOGITS
     Baptist
    0.37
     inspirations
    0.37
     glut
    0.36
    OMBRE
    0.35
    Prepar
    0.35
    梓
    0.34
     inspirational
    0.33
    assadors
    0.33
     phúc
    0.33
     inspiration
    0.33
    Activations Density 0.012%

    No Known Activations