© 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. 30859
    Prev
    Next
    INDEX
    Explanations

    reporting claims or statements

    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
    வடிக்க
    0.36
     глаза
    0.34
     લાવ
    0.34
     Cdc
    0.34
    哌
    0.33
    ικού
    0.33
    vcxproj
    0.33
    癤
    0.33
     оказыва
    0.32
     Deserialize
    0.32
    POSITIVE LOGITS
     says
    0.77
     zegt
    0.68
    says
    0.66
     said
    0.64
     mengatakan
    0.64
     sagt
    0.61
     säger
    0.60
     suggests
    0.59
     described
    0.58
    认为
    0.58
    Activations Density 0.056%

    No Known Activations