© 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. 79559
    Prev
    Next
    INDEX
    Explanations

    riding

    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
    <0x80>
    1.53
    ري
    1.51
    ओं
    1.23
    ы
    1.16
    ación
    1.13
    ции
    1.13
    ात
    1.13
    もら
    1.11
    {
    1.08
    ação
    1.07
    POSITIVE LOGITS
     is
    1.76
    ח
    1.58
     to
    1.40
    UT
    1.30
    quela
    1.30
    RAL
    1.23
    ма
    1.23
    heartedly
    1.23
    ')
    1.22
    AT
    1.21
    Activations Density 0.000%

    No Known Activations