© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213079
    Prev
    Next
    INDEX
    Explanations

    modest proposal

    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_5_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
    ด
    1.13
    ל
    0.94
    ்
    0.88
    או
    0.87
    אם
    0.83
    dienst
    0.83
    durch
    0.83
    و
    0.82
    ا
    0.81
    ו
    0.81
    POSITIVE LOGITS
    is
    1.24
    </h2>
    1.20
    in
    1.16
    지
    1.15
     (
    1.14
     in
    1.10
    <0x0D>
    1.05
     to
    1.01
    х
    0.97
    ve
    0.95
    Activations Density 0.000%

    No Known Activations