© 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. 68014
    Prev
    Next
    INDEX
    Explanations

    beaver

    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
    aians
    0.48
    DRIVER
    0.47
    drivers
    0.44
    Group
    0.43
    Drivers
    0.42
    driver
    0.40
    '][$
    0.38
    擂
    0.38
    ⠊
    0.38
    ைய
    0.38
    POSITIVE LOGITS
     ponds
    0.47
     Nyl
    0.43
     dams
    0.41
     pond
    0.39
     meditate
    0.39
     laminated
    0.39
     Archim
    0.38
     redwood
    0.38
     pounding
    0.38
    линд
    0.38
    Activations Density 0.000%

    No Known Activations