© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236650
    Prev
    Next
    INDEX
    Explanations

    if conn or mydb

    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_25_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
     año
    0.46
    Año
    0.46
    𝔀
    0.44
     Tahun
    0.43
    歳の
    0.43
     rectMode
    0.42
     focussing
    0.42
     =",
    0.42
    ᆭ
    0.41
     varie
    0.41
    POSITIVE LOGITS
     Everything
    0.42
     Ugly
    0.39
     Greedy
    0.39
     Excessive
    0.38
     Revival
    0.38
     Tonight
    0.38
    <0x0D>
    0.37
    0.37
     Today
    0.37
     Clever
    0.36
    Activations Density 0.000%

    No Known Activations