© 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. 142600
    Prev
    Next
    INDEX
    Explanations

    piper

    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
     Niels
    0.47
     pard
    0.43
     pardon
    0.42
     Z
    0.39
     McMahon
    0.39
     Bailey
    0.39
     Th
    0.38
    स्ती
    0.38
     Buk
    0.38
     Body
    0.37
    POSITIVE LOGITS
    MTAB
    0.44
    erkraut
    0.43
    ceiver
    0.41
    賁
    0.40
    никами
    0.40
     pérdida
    0.40
    банк
    0.40
     ಉಪಯೋಗ
    0.39
    ชา
    0.39
    FileChooser
    0.38
    Activations Density 0.000%

    No Known Activations