© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63885
    Prev
    Next
    INDEX
    Explanations

    It

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     demands
    0.50
     quickly
    0.43
     cepat
    0.42
    趋
    0.41
     मांगे
    0.40
    Suff
    0.40
     मागणी
    0.39
     Winery
    0.39
     opportune
    0.38
     demandas
    0.38
    POSITIVE LOGITS
    sound
    0.41
     Vener
    0.41
    doch
    0.40
    枒
    0.39
    ለጠ
    0.39
     SOUND
    0.38
     Vulner
    0.37
     Evidently
    0.37
     sound
    0.36
     connecting
    0.36
    Activations Density 0.015%

    No Known Activations