© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17627
    Prev
    Next
    INDEX
    Explanations

    HTML title tag

    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_40_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
     अराउंड
    0.33
    orea
    0.32
     સફેદ
    0.32
    பை
    0.32
    装着
    0.32
     الإنترنت
    0.32
    aconda
    0.31
     적
    0.31
    ட்ரா
    0.31
     oportun
    0.31
    POSITIVE LOGITS
    addock
    0.33
    Speakers
    0.33
    
    0.33
    ้าย
    0.32
     Пи
    0.32
     ऑग
    0.32
    sender
    0.32
    Przy
    0.31
     trot
    0.31
    ໋
    0.31
    Activations Density 0.004%

    No Known Activations