© 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. 194468
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specific terms

    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
     saz
    0.33
     doute
    0.32
     schre
    0.32
    +}^{
    0.31
     cry
    0.31
     تجه
    0.31
     mysteriously
    0.31
    *((*
    0.31
     hydrolysis
    0.30
     catar
    0.30
    POSITIVE LOGITS
     उसका
    0.39
     उसकी
    0.37
     उसको
    0.37
     njegov
    0.36
     njegova
    0.35
    但他
    0.34
    为其
    0.34
     его
    0.33
     ей
    0.33
    Its
    0.32
    Activations Density 0.003%

    No Known Activations