© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130249
    Prev
    Next
    INDEX
    Explanations

    dirección constante, completa, física, IP, única, opuesta

    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
    {
    1.67
    Ü
    1.41
    t
    1.22
    AG
    1.20
    (
    1.19
    ม
    1.19
    ORT
    1.14
    ’
    1.14
    INI
    1.13
     allemand
    1.12
    POSITIVE LOGITS
    ре
    1.05
    ра
    0.92
    iciency
    0.89
    ado
    0.88
    لی
    0.88
    ids
    0.86
    ρα
    0.84
    де
    0.84
    ग्रस्त
    0.84
    เร็จ
    0.84
    Activations Density 0.000%

    No Known Activations