© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61101
    Prev
    Next
    INDEX
    Explanations

    to confine

    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_2_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
     as
    1.30
     обита
    0.85
     дерев
    0.84
     আসামি
    0.84
     εται
    0.82
     extravagant
    0.82
     обши
    0.81
     고
    0.81
     from
    0.80
     excepc
    0.80
    POSITIVE LOGITS
    an
    2.19
    is
    2.06
    a
    1.84
    i
    1.77
    in
    1.68
    u
    1.50
    o
    1.48
    ة
    1.43
    l
    1.41
    it
    1.37
    Activations Density 0.001%

    No Known Activations