© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42824
    Prev
    Next
    INDEX
    Explanations

    code comments and input validation

    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_13_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
    𝚙
    0.36
     restant
    0.33
    ಿಂದ
    0.32
    P
    0.31
    எஸ்
    0.31
     resulta
    0.30
     powied
    0.30
    L
    0.30
     manic
    0.30
    ńst
    0.29
    POSITIVE LOGITS
    )，
    0.35
    ва
    0.33
    )،
    0.31
    阂
    0.31
     Zeit
    0.30
    ：《
    0.30
    棤
    0.29
     Qualität
    0.29
    ：“
    0.29
    írás
    0.29
    Activations Density 0.001%

    No Known Activations