© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13597
    Prev
    Next
    INDEX
    Explanations

    encyclopedia, wikipedia, websites

    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_15_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
     $\
    0.31
    uan
    0.29
     $
    0.27
    aiman
    0.27
    ís
    0.26
    ating
    0.25
    ic
    0.25
    ual
    0.25
    ated
    0.25
    uer
    0.25
    POSITIVE LOGITS
    墀
    0.33
    嚩
    0.28
    羰
    0.28
     VCO
    0.27
    苌
    0.27
     Commissary
    0.26
    FCO
    0.26
    鉞
    0.26
     offsetX
    0.26
    риал
    0.26
    Activations Density 0.007%

    No Known Activations