© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88531
    Prev
    Next
    INDEX
    Explanations

    opa, oshi, igi, anka, ppo, Opel, opus

    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_3_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
    a
    0.73
    欱
    0.73
    r
    0.71
    н
    0.68
    </h2>
    0.65
    왑
    0.63
     on
    0.63
     Inflammation
    0.60
    zelf
    0.59
     Appet
    0.59
    POSITIVE LOGITS
    ’
    0.85
    '
    0.71
    но
    0.71
    ้าน
    0.67
    <0x8B>
    0.65
    ั
    0.64
    ının
    0.63
     derivation
    0.61
    ू
    0.61
    ፣
    0.61
    Activations Density 0.006%

    No Known Activations