© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194491
    Prev
    Next
    INDEX
    Explanations

    bound, bounding

    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_4_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
    {
    0.88
    ,
    0.88
    います
    0.88
    (~
    0.68
    I
    0.68
    "^
    0.66
    ㈣
    0.61
    faat
    0.61
    0
    0.61
    $
    0.60
    POSITIVE LOGITS
    in
    1.39
     in
    1.14
    ک
    1.01
     search
    0.98
     obtain
    0.95
    มอง
    0.95
    l
    0.89
    ul
    0.88
     seek
    0.88
     allocate
    0.86
    Activations Density 0.000%

    No Known Activations