© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230636
    Prev
    Next
    INDEX
    Explanations

    first choice

    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_6_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
    on
    1.11
     выбо
    0.99
     on
    0.98
    );
    0.95
    ق
    0.86
    n
    0.85
    وفي
    0.84
     парамет
    0.83
    థ
    0.83
    k
    0.82
    POSITIVE LOGITS
    2
    1.00
    ை
    0.96
    3
    0.96
    ı
    0.91
    Expiration
    0.90
    ا
    0.89
    ă
    0.88
    ۲
    0.86
    \
    0.84
    า
    0.83
    Activations Density 0.000%

    No Known Activations