© 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. 80076
    Prev
    Next
    INDEX
    Explanations

    historian and dates

    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
    Leonardo
    0.46
    煙
    0.45
     Leonardo
    0.43
    Meal
    0.40
     аэро
    0.40
    烟
    0.39
    潼
    0.36
    Rena
    0.36
    体验
    0.36
     appareils
    0.36
    POSITIVE LOGITS
     irish
    0.43
    initions
    0.40
     profane
    0.40
     prohibitions
    0.39
     cds
    0.37
     lounge
    0.37
    蚝
    0.37
     stimulate
    0.36
     Omaha
    0.36
     crushed
    0.36
    Activations Density 0.008%

    No Known Activations