© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132881
    Prev
    Next
    INDEX
    Explanations

    dé, pré

    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_1_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
    ig
    1.29
    。
    1.13
    ların
    0.93
    ק
    0.91
    ne
    0.91
    ।
    0.88
    larının
    0.87
    lt
    0.86
    lerinin
    0.86
    st
    0.85
    POSITIVE LOGITS
    ו
    1.42
     as
    1.24
     de
    1.16
    س
    1.16
    ス
    1.15
    с
    1.13
     have
    1.11
    দের
    1.09
    have
    1.09
    en
    1.09
    Activations Density 0.000%

    No Known Activations