© 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. 8349
    Prev
    Next
    INDEX
    Explanations

    LM Studio

    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
    TIM
    0.39
    ք
    0.38
     quảng
    0.35
    বের
    0.34
    renn
    0.34
     상당
    0.34
    බැ
    0.34
    鹂
    0.34
     größ
    0.33
    발
    0.33
    POSITIVE LOGITS
     zm
    0.55
    ageddon
    0.47
    ühle
    0.44
    وضوع
    0.44
    جموع
    0.43
    ismatch
    0.43
    irnov
    0.41
    iany
    0.40
    ιουργ
    0.40
    ujemy
    0.38
    Activations Density 0.069%

    No Known Activations