© 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. 215237
    Prev
    Next
    INDEX
    Explanations

    URLs and time calculations

    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
    PrefabAsset
    0.40
    loyd
    0.36
    cm
    0.34
     JOSEPH
    0.33
    エ
    0.33
    thru
    0.32
    Region
    0.32
     THEIR
    0.32
     regione
    0.32
     Regione
    0.32
    POSITIVE LOGITS
     चम्म
    0.32
     BrowserWindow
    0.32
     influences
    0.31
     Archives
    0.31
     archives
    0.31
    的标准
    0.31
     handlebars
    0.31
    靜
    0.31
     静
    0.31
     椅
    0.31
    Activations Density 0.000%

    No Known Activations