© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176172
    Prev
    Next
    INDEX
    Explanations

    cheap flights

    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_20_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
    .,
    0.52
    io
    0.50
    ."
    0.49
     explicit
    0.47
     configur
    0.46
     @"
    0.45
    /
    0.45
     Kontakt
    0.45
    Noir
    0.45
    ",
    0.44
    POSITIVE LOGITS
     selber
    0.46
    牟
    0.46
     منہ
    0.44
    indungan
    0.43
     เส้น
    0.43
    시대
    0.43
     ಅನುಪ
    0.43
    OutOfBounds
    0.42
    strlen
    0.42
     亻
    0.42
    Activations Density 0.000%

    No Known Activations