© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146044
    Prev
    Next
    INDEX
    Explanations

    Break

    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_59_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
    Glowing
    0.39
    Golden
    0.38
    ισμό
    0.37
    }^{*}
    0.35
     новий
    0.35
    BH
    0.35
    ouni
    0.35
    իտ
    0.34
    iseerd
    0.34
    归
    0.34
    POSITIVE LOGITS
     Up
    0.60
    er
    0.48
    wrs
    0.45
    ERS
    0.44
     Down
    0.44
    ER
    0.43
    ер
    0.43
    της
    0.43
    ers
    0.41
    вка
    0.41
    Activations Density 0.000%

    No Known Activations