© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47053
    Prev
    Next
    INDEX
    Explanations

    ki

    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_10_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
    crose
    0.19
     є
    0.17
    oute
    0.17
    amente
    0.16
    ire
    0.16
    oul
    0.16
    asyon
    0.16
    aves
    0.16
    ic
    0.16
    uff
    0.16
    POSITIVE LOGITS
    s
    0.20
    g
    0.20
    。
    0.17
    tu
    0.16
    e
    0.16
    ים
    0.15
    בק
    0.15
    sal
    0.15
    ཥ
    0.14
    tan
    0.14
    Activations Density 0.005%

    No Known Activations