© 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. 204638
    Prev
    Next
    INDEX
    Explanations

    parallelization

    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
    il
    0.98
    ين
    0.76
    ap
    0.75
    ut
    0.71
    <0x0D>
    0.70
    ೊ
    0.70
    ens
    0.69
    á
    0.64
    يل
    0.63
    ור
    0.62
    POSITIVE LOGITS
    ↵
    0.88
    เป็น
    0.82
    ใน
    0.80
    在
    0.80
    u
    0.71
    ໃນ
    0.70
    ا
    0.70
    ם
    0.69
    لی
    0.68
    RO
    0.68
    Activations Density 0.000%

    No Known Activations