© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115629
    Prev
    Next
    INDEX
    Explanations

    numbers followed by comma or semicolon

    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_27_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
    вање
    0.36
    ލ
    0.36
    oelectronic
    0.33
     wag
    0.33
     Darn
    0.33
    就算是
    0.33
     disability
    0.32
     indistinct
    0.32
     maritime
    0.32
     पिक
    0.32
    POSITIVE LOGITS
    \&
    0.40
    Dividend
    0.39
    SF
    0.39
    Best
    0.37
     Balt
    0.37
    Checksum
    0.37
    ++];
    0.37
    VF
    0.36
     Dividend
    0.35
    Def
    0.35
    Activations Density 0.011%

    No Known Activations