© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201823
    Prev
    Next
    INDEX
    Explanations

    names and words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Sensory
    0.42
     jok
    0.40
    auche
    0.38
     ਕਰੋ
    0.36
    กฏ
    0.35
    ประโยชน์
    0.35
     проис
    0.34
    顯
    0.34
    Connector
    0.34
    ೃದ್ಧ
    0.34
    POSITIVE LOGITS
     Phas
    0.45
    Fixed
    0.40
     EDWARD
    0.39
     Fixed
    0.38
     سمع
    0.36
    Disposition
    0.36
     Remains
    0.36
    Пла
    0.35
     merak
    0.35
     Petros
    0.35
    Activations Density 0.001%

    No Known Activations