© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133293
    Prev
    Next
    INDEX
    Explanations

    duty respect

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     처
    0.44
    处
    0.40
    Mana
    0.38
    Aik
    0.37
    幄
    0.37
     প্রত
    0.36
    RV
    0.36
    )}`;
    0.34
     ))}
    0.34
    ódromo
    0.34
    POSITIVE LOGITS
    盡
    0.54
    尽
    0.50
    Eff
    0.46
    eff
    0.46
     Eff
    0.46
     glutathione
    0.44
    GLAND
    0.43
     eff
    0.43
     EFF
    0.41
    補
    0.41
    Activations Density 0.006%

    No Known Activations