© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34658
    Prev
    Next
    INDEX
    Explanations

    comparing models

    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_50_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
     qí
    0.35
    념
    0.33
    𝕄
    0.32
     lata
    0.32
     mediator
    0.32
     Enum
    0.31
    АТО
    0.31
    র্শ
    0.31
     ચ
    0.31
     ai
    0.31
    POSITIVE LOGITS
    <table>
    0.40
    ")){
    0.40
    [](
    0.32
    پور
    0.32
    batt
    0.32
    `,`
    0.31
    ")):
    0.31
     തന്നെയാണ്
    0.31
    bandage
    0.31
    __))
    0.31
    Activations Density 0.024%

    No Known Activations