© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125158
    Prev
    Next
    INDEX
    Explanations

    University of Maryland, Pakistan, Punjab

    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_37_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
     Loretta
    0.43
     cloning
    0.40
     ();
    0.38
     Equation
    0.38
     winding
    0.38
     Marker
    0.38
     INDUSTR
    0.37
     ಕ್ಷೇತ್ರದಲ್ಲಿ
    0.37
    ualmente
    0.37
     sipping
    0.37
    POSITIVE LOGITS
    CMP
    0.40
    CPM
    0.38
    사실
    0.38
    Child
    0.37
    审核
    0.37
    呼
    0.37
    Comparable
    0.37
    ORK
    0.37
    hrt
    0.37
    Дата
    0.37
    Activations Density 0.000%

    No Known Activations