© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211693
    Prev
    Next
    INDEX
    Explanations

    attracting attention

    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_5_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
    1.75
    for
    1.27
    IS
    1.23
    by
    1.23
    l
    1.20
    8
    1.20
    still
    1.19
    Q
    1.16
    W
    1.15
    be
    1.10
    POSITIVE LOGITS
    <0x80>
    2.03
    ０
    1.52
    αν
    1.41
    িয়া
    1.29
    ین
    1.27
    یک
    1.27
    িয়া
    1.27
    ِی
    1.25
    вати
    1.18
    лло
    1.17
    Activations Density 0.000%

    No Known Activations