© 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. 104640
    Prev
    Next
    INDEX
    Explanations

    segunda, segurança, segredo

    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
    는
    1.22
    ع
    1.20
    "
    1.16
    ية
    1.16
    to
    1.14
    지
    1.14
    ת
    1.13
    ت
    1.12
    전
    1.11
    '
    1.07
    POSITIVE LOGITS
    uk
    0.96
     οποίο
    0.96
     că
    0.95
     și
    0.93
     répondre
    0.93
    .';
    0.93
    рты
    0.92
    üş
    0.91
    رير
    0.91
    rilor
    0.89
    Activations Density 0.000%

    No Known Activations