© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13386
    Prev
    Next
    INDEX
    Explanations

    Lin, Fin, lim

    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_40_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
     productive
    0.38
    なあ
    0.38
    cmt
    0.36
    Corpor
    0.36
    ointe
    0.35
    𝘆
    0.35
    욥
    0.35
    <unused24>
    0.34
     substantial
    0.34
    baz
    0.33
    POSITIVE LOGITS
     Anfang
    0.39
    Nhap
    0.38
    放下
    0.38
     flott
    0.37
    निव
    0.37
     แห่ง
    0.37
     Ту
    0.36
     Landkreis
    0.36
     फर्श
    0.36
     ris
    0.35
    Activations Density 0.022%

    No Known Activations