© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141684
    Prev
    Next
    INDEX
    Explanations

    imai, ogados, vidas, indo

    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
    ی
    1.77
    ки
    1.59
     the
    1.53
    ри
    1.53
    ι
    1.51
    the
    1.49
    ни
    1.47
    <0x80>
    1.38
    पणे
    1.37
     і
    1.31
    POSITIVE LOGITS
     that
    1.78
    。
    1.60
     for
    1.47
     was
    1.27
     Interess
    1.25
     Been
    1.24
     的
    1.20
    ب
    1.18
    滏
    1.16
    </h4>
    1.13
    Activations Density 0.000%

    No Known Activations