© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35687
    Prev
    Next
    INDEX
    Explanations

    sexual assault service

    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
    ↵
    1.08
    ↵↵
    1.05
    </b>
    1.04
    </u>
    0.90
    ?
    0.90
    </strong>
    0.83
    </h3>
    0.80
    </i>
    0.79
    !
    0.79
    </sub>
    0.75
    POSITIVE LOGITS
    ătoare
    0.73
    ﻁ
    0.72
    ټر
    0.70
    ăți
    0.67
    𝑭
    0.67
    ﻬ
    0.66
    レポート
    0.65
     مدير
    0.64
     méthodique
    0.64
    AIR
    0.64
    Activations Density 0.008%

    No Known Activations