© 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. 228667
    Prev
    Next
    INDEX
    Explanations

    talk like a persona

    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
    ت
    1.16
    ل
    1.15
    ع
    1.00
    src
    1.00
    the
    0.98
    lə
    0.98
    る
    0.97
    inį
    0.96
    ".
    0.96
    ك
    0.94
    POSITIVE LOGITS
    <0x0D>
    1.03
    om
    1.02
    ing
    0.96
    </h2>
    0.93
    ů
    0.93
    </b>
    0.93
    o
    0.91
    r
    0.86
    ｒ
    0.84
    ân
    0.83
    Activations Density 0.001%

    No Known Activations