© 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. 69107
    Prev
    Next
    INDEX
    Explanations

    co

    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
    ~~
    0.44
    ownik
    0.41
     Charts
    0.40
    lients
    0.39
     stationary
    0.38
    atures
    0.37
     mobile
    0.37
     toe
    0.37
    Chart
    0.37
    Nik
    0.37
    POSITIVE LOGITS
    க்கல்
    0.37
     comentário
    0.37
    櫃
    0.37
    Lux
    0.36
    ânia
    0.36
     preclude
    0.36
    テナ
    0.36
     Ángel
    0.36
    コメント
    0.35
     ort
    0.35
    Activations Density 0.001%

    No Known Activations