© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209784
    Prev
    Next
    INDEX
    Explanations

    fail-safes, safety, behavior

    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_5_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
     Have
    0.98
     Been
    0.98
     by
    0.90
     Transportation
    0.88
    .</
    0.88
     Unable
    0.84
    </span>
    0.83
     for
    0.82
     That
    0.82
     They
    0.82
    POSITIVE LOGITS
    al
    1.63
    ن
    1.55
    ي
    1.53
    ва
    1.45
    ри
    1.41
    ための
    1.33
    ν
    1.33
    𓏧
    1.31
    ນ
    1.28
    ກ
    1.28
    Activations Density 0.000%

    No Known Activations