© 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. 202252
    Prev
    Next
    INDEX
    Explanations

    Porsche

    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
    大な
    0.39
    堰
    0.39
    скім
    0.38
    aluronic
    0.38
     الخمسه
    0.36
     شلون
    0.36
    сног
    0.36
    五
    0.36
    Five
    0.35
    spaced
    0.35
    POSITIVE LOGITS
    mend
    0.44
     GR
    0.43
    罘
    0.40
    GR
    0.39
     Lauf
    0.39
     dell
    0.38
     tray
    0.38
     स्वत
    0.38
     IR
    0.37
     max
    0.36
    Activations Density 0.001%

    No Known Activations