© 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. 247113
    Prev
    Next
    INDEX
    Explanations

    database cursor operations

    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
     ADMINISTRATION
    0.38
     Audience
    0.36
     ADMIN
    0.36
    ርግ
    0.35
    ICATION
    0.34
    *\
    0.34
     एलिमेंट
    0.33
    soc
    0.33
    ubation
    0.33
     Assertion
    0.33
    POSITIVE LOGITS
     அற
    0.35
     ವರ್
    0.34
    ഋ
    0.34
    dataPath
    0.33
    gele
    0.33
    แปล
    0.33
    창
    0.33
    創
    0.33
    ವರ್
    0.32
    needle
    0.32
    Activations Density 0.001%

    No Known Activations