© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145633
    Prev
    Next
    INDEX
    Explanations

    intimacy

    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_0_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
    </h3>
    1.99
    ك
    1.84
    </strong>
    1.73
    </h2>
    1.60
    </h1>
    1.55
    ;
    1.49
    </h5>
    1.46
    <0x0D>
    1.46
    </h6>
    1.44
    </em>
    1.44
    POSITIVE LOGITS
    r
    2.22
    n
    1.95
    la
    1.88
    ت
    1.76
    る
    1.75
    l
    1.68
    is
    1.67
    li
    1.53
    los
    1.48
    ר
    1.45
    Activations Density 0.000%

    No Known Activations