© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198808
    Prev
    Next
    INDEX
    Explanations

    just then can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    ursing
    0.44
     TES
    0.41
    translate
    0.40
     cazul
    0.40
     CCS
    0.40
     áreas
    0.38
    📏
    0.38
    ținut
    0.38
    apaccay
    0.38
    擇
    0.38
    POSITIVE LOGITS
     dead
    0.44
     candidate
    0.44
     रा
    0.40
    唯一的
    0.40
    جهة
    0.39
     unterschiedlich
    0.38
    အချိန်
    0.38
     sparrow
    0.37
     неодно
    0.36
     Ciebie
    0.36
    Activations Density 0.000%

    No Known Activations