© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80454
    Prev
    Next
    INDEX
    Explanations

    GIVE CATEGORY NAME

    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_0_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
    an
    1.66
    נ
    1.53
    는
    1.45
    t
    1.43
    ۔
    1.41
    是谁
    1.39
    ב
    1.38
    h
    1.36
    是
    1.36
    ر
    1.35
    POSITIVE LOGITS
    𝟬
    1.44
    ０
    1.41
    な
    1.25
    ೦
    1.20
    ۰
    1.20
    ᱐
    1.19
    𝟎
    1.17
    ла
    1.13
    !\!\
    1.08
    した
    1.07
    Activations Density 0.003%

    No Known Activations