© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31262
    Prev
    Next
    INDEX
    Explanations

    Bolt, Nut, Washer, Tolerance

    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_40_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
     greedy
    0.40
    $\$
    0.40
    /\/
    0.38
    ampunk
    0.38
     tyrannical
    0.38
    хар
    0.37
     справед
    0.37
    arming
    0.37
    untur
    0.37
     '$
    0.37
    POSITIVE LOGITS
    Quality
    0.50
     accuracy
    0.42
     Accuracy
    0.42
     Quality
    0.41
     tolerance
    0.41
     quality
    0.40
     Tolerance
    0.40
    quality
    0.40
    </tr>
    0.39
    HS
    0.38
    Activations Density 0.014%

    No Known Activations