© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39486
    Prev
    Next
    INDEX
    Explanations

    @, !, "Son", "While", "Headline"

    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
    </b>
    0.80
    </h1>
    0.78
    ر
    0.78
    р
    0.74
    ↵
    0.73
     chinois
    0.73
    ния
    0.73
    ний
    0.72
    ه
    0.72
     déficit
    0.71
    POSITIVE LOGITS
    sa
    0.99
    스
    0.89
    s
    0.84
    𝓼
    0.83
    $+
    0.82
    ac
    0.80
    変数
    0.79
    ्स
    0.75
     to
    0.74
    EX
    0.74
    Activations Density 0.036%

    No Known Activations