© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39559
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    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_57_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
    เค
    0.39
    怖い
    0.39
    袮
    0.39
    
    0.38
    姜
    0.36
     ced
    0.36
     বিশেষণ
    0.35
    Notre
    0.35
     Ginger
    0.35
     ========
    0.35
    POSITIVE LOGITS
    ന്തി
    0.40
    untar
    0.39
    비
    0.39
    사항
    0.38
    على
    0.37
    utral
    0.37
    ંત
    0.37
    гах
    0.37
    itor
    0.36
    עי
    0.36
    Activations Density 0.000%

    No Known Activations