© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180400
    Prev
    Next
    INDEX
    Explanations

    unknown or not specified

    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_24_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
     ravaged
    0.30
     ра
    0.30
     Hardly
    0.28
     aku
    0.28
     Zasshi
    0.28
     rav
    0.27
     stoned
    0.27
     .{
    0.26
     ferrug
    0.25
     rog
    0.25
    POSITIVE LOGITS
     ڪري
    0.27
     convenience
    0.26
     achieves
    0.26
     seems
    0.25
    Band
    0.24
     overcomes
    0.24
     tiện
    0.24
    tochrome
    0.24
     corresponds
    0.24
     speakers
    0.23
    Activations Density 0.004%

    No Known Activations