© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2234
    Prev
    Next
    INDEX
    Explanations

    fundamental building block

    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_39_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
    ⸨
    0.42
     Wrigley
    0.40
    TOOLBAR
    0.39
     Tolstoy
    0.38
     bedrijf
    0.35
    ினார்
    0.35
     dham
    0.34
    ICKET
    0.34
    ᡳ
    0.34
     {#
    0.33
    POSITIVE LOGITS
    Halloween
    0.37
     Nice
    0.36
     nice
    0.36
    nice
    0.35
    orme
    0.35
    ano
    0.34
     sine
    0.33
    famous
    0.33
     critical
    0.33
    Nice
    0.32
    Activations Density 0.145%

    No Known Activations