© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142929
    Prev
    Next
    INDEX
    Explanations

    theorize

    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_0_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
     It
    1.61
    ع
    1.38
    ι
    1.20
    anya
    1.16
    야
    1.16
    ona
    1.15
    पणे
    1.14
    ever
    1.11
    ab
    1.09
    வும்
    1.09
    POSITIVE LOGITS
    ק
    1.95
    К
    1.80
     by
    1.69
    ン
    1.63
     crucified
    1.55
     is
    1.52
     of
    1.48
     hôtels
    1.45
    О
    1.45
    3
    1.45
    Activations Density 0.000%

    No Known Activations