© 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. 142827
    Prev
    Next
    INDEX
    Explanations

    Quentin Tarantino, tenido, personales

    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
     as
    1.69
    ق
    1.60
     for
    1.48
    서
    1.39
    ak
    1.33
    सामान्यीकृत
    1.27
    il
    1.22
    t
    1.22
    对
    1.20
    κ
    1.18
    POSITIVE LOGITS
    ra
    1.80
    -
    1.73
    ו
    1.41
    ла
    1.38
    ور
    1.27
    なります
    1.27
    <0x0D>
    1.24
    я
    1.20
    ี
    1.19
    ва
    1.16
    Activations Density 0.000%

    No Known Activations