© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76349
    Prev
    Next
    INDEX
    Explanations

    sliding door track

    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_31_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
    Tennis
    0.37
    жный
    0.35
    ៍
    0.35
    Dust
    0.34
    ގައި
    0.34
    ሳት
    0.34
     Tennis
    0.33
     ::=
    0.33
    чный
    0.33
    LEMN
    0.32
    POSITIVE LOGITS
     Continuando
    0.39
     checked
    0.37
     partition
    0.37
     koh
    0.36
     fopen
    0.36
     Open
    0.35
     rata
    0.35
     sullo
    0.35
    upan
    0.34
    iya
    0.34
    Activations Density 0.003%

    No Known Activations