© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232568
    Prev
    Next
    INDEX
    Explanations

    cut

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     MDLVertex
    0.37
    ⚉
    0.36
     $\#
    0.35
    ógio
    0.35
    ང
    0.34
    敚
    0.33
     hern
    0.33
    াব
    0.33
     Avg
    0.32
     মৃ
    0.32
    POSITIVE LOGITS
     cut
    2.97
    Cut
    2.64
    cut
    2.61
     Cut
    2.58
     cuts
    2.53
     cutting
    2.47
     CUT
    2.45
    切
    2.41
    cuts
    2.39
     cắt
    2.38
    Activations Density 0.028%

    No Known Activations