© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2328
    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_44_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
    欒
    0.35
    ऱ्यावर
    0.35
    करार
    0.35
     lookup
    0.34
    dinger
    0.34
     граф
    0.33
    ྫ
    0.33
     Levels
    0.33
    திகளை
    0.33
    umsi
    0.32
    POSITIVE LOGITS
     cut
    3.34
     cuts
    3.05
    Cut
    3.00
     Cut
    2.98
    cut
    2.94
     Cuts
    2.72
     CUT
    2.66
    cuts
    2.59
    CUT
    2.50
    切
    2.42
    Activations Density 0.196%

    No Known Activations