© 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. 32899
    Prev
    Next
    INDEX
    Explanations

    customer support chat phone

    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
     call
    2.88
    call
    2.59
     Call
    2.53
    Call
    2.52
     CALL
    2.11
    CALL
    2.03
     कॉल
    1.82
    呼
    1.73
     calls
    1.59
     Calls
    1.52
    POSITIVE LOGITS
    ENTIAL
    0.38
     பால்
    0.37
    নীয়
    0.36
     Trim
    0.35
    ِيم
    0.35
     equipamento
    0.35
     ಪು
    0.35
     Pape
    0.35
    鑰
    0.35
     टैबलेट
    0.34
    Activations Density 0.036%

    No Known Activations