© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206405
    Prev
    Next
    INDEX
    Explanations

    not around

    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_20_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
    ပြည်
    0.43
    👷
    0.41
     Plymouth
    0.40
     Completion
    0.39
     Edw
    0.39
     Flanders
    0.39
     huit
    0.39
    ification
    0.38
     viii
    0.38
    ⵚ
    0.38
    POSITIVE LOGITS
    errated
    0.39
    ۇل
    0.36
    LINE
    0.35
     autoload
    0.35
    Whis
    0.34
    getLevel
    0.34
     coupler
    0.34
     agad
    0.34
    曲
    0.33
    butanol
    0.33
    Activations Density 0.001%

    No Known Activations