© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53638
    Prev
    Next
    INDEX
    Explanations

    select option across languages

    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_55_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
    方
    0.44
    期
    0.43
     fang
    0.43
     phương
    0.41
    method
    0.40
     Fang
    0.40
     Method
    0.39
    stage
    0.39
    combined
    0.38
    lude
    0.37
    POSITIVE LOGITS
     !_
    0.42
    침
    0.42
    射
    0.39
    码
    0.37
     cosi
    0.37
    Allora
    0.36
     STATION
    0.36
     Così
    0.35
     まま
    0.35
     Benim
    0.35
    Activations Density 0.006%

    No Known Activations