© 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. 82157
    Prev
    Next
    INDEX
    Explanations

    UX design and research

    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
    ل
    1.88
    ל
    1.64
    ट
    1.57
     be
    1.55
    ä
    1.55
    ро
    1.41
    то
    1.40
    л
    1.38
     on
    1.36
    ル
    1.31
    POSITIVE LOGITS
    y
    1.48
    larımız
    1.21
    ların
    1.16
    ла
    1.12
    i
    1.11
     in
    1.07
    The
    1.07
    gery
    1.06
    tan
    1.02
     国家
    1.02
    Activations Density 0.000%

    No Known Activations