© 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. 44057
    Prev
    Next
    INDEX
    Explanations

    sun sign

    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
    ן
    0.89
    м
    0.88
    자
    0.86
    ক
    0.84
    ش
    0.80
    t
    0.79
    ﺀ
    0.77
    dır
    0.74
    ड
    0.73
    й
    0.72
    POSITIVE LOGITS
    in
    0.96
    ig
    0.71
    us
    0.68
    am
    0.67
    </h2>
    0.67
     படித்த
    0.66
    𝐁
    0.65
    iest
    0.64
    aket
    0.63
    ter
    0.62
    Activations Density 0.004%

    No Known Activations