© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84376
    Prev
    Next
    INDEX
    Explanations

    error messages to stderr

    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_23_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
    fly
    0.41
     flew
    0.41
    윙
    0.40
     publicly
    0.39
     öffentliche
    0.39
     anthrop
    0.38
    wne
    0.38
     ocen
    0.38
     dwelt
    0.38
    chnitt
    0.37
    POSITIVE LOGITS
     পুত্র
    0.43
    აცია
    0.40
     لذا
    0.40
    Dat
    0.38
     коро
    0.38
    柺
    0.38
    вшийся
    0.37
     datac
    0.37
     Dat
    0.36
     Corrosion
    0.36
    Activations Density 0.001%

    No Known Activations