© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164448
    Prev
    Next
    INDEX
    Explanations

    founder or owner names

    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
    Deer
    0.42
    刺激
    0.39
     Dialer
    0.39
    要求
    0.38
     검
    0.38
     HIG
    0.38
    SpecID
    0.38
    Breakfast
    0.37
    毒
    0.37
     закры
    0.37
    POSITIVE LOGITS
     sap
    0.38
     whistling
    0.38
    enschaft
    0.38
     personales
    0.38
    ènement
    0.37
     license
    0.37
     Heter
    0.36
     निजामा
    0.36
     salary
    0.36
     ownership
    0.36
    Activations Density 0.005%

    No Known Activations