© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35203
    Prev
    Next
    INDEX
    Explanations

    sign/indicate potential issues

    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_31_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
     EF
    0.37
     랜
    0.31
    Rand
    0.29
     Falls
    0.29
     cuanto
    0.29
     proc
    0.29
     Cut
    0.29
    ர்த்த
    0.28
     Nur
    0.28
    രാണ്
    0.28
    POSITIVE LOGITS
    worn
    0.29
     offended
    0.28
    ষ
    0.27
    قه
    0.27
     खोले
    0.27
    紵
    0.27
    >';
    0.27
    shoring
    0.27
     तहरीर
    0.27
     stacked
    0.26
    Activations Density 0.023%

    No Known Activations