© 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. 43692
    Prev
    Next
    INDEX
    Explanations

    excellent value

    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
    </h3>
    1.00
    </strong>
    0.95
    </em>
    0.86
    ει
    0.76
    見える
    0.75
    </h5>
    0.73
     libera
    0.72
    </h6>
    0.70
    </h2>
    0.69
    </sub>
    0.69
    POSITIVE LOGITS
    ר
    0.98
    то
    0.96
    K
    0.92
    2
    0.85
    q
    0.84
    3
    0.82
    ל
    0.82
    J
    0.75
    in
    0.75
    M
    0.75
    Activations Density 0.006%

    No Known Activations