© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 213825
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_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
     AND
    0.55
    腚
    0.54
    멧
    0.51
    ISTRATION
    0.48
     BUT
    0.46
     Ollie
    0.46
    AND
    0.46
    楞
    0.46
    fans
    0.46
     Hines
    0.46
    POSITIVE LOGITS
     emergencia
    0.58
     premier
    0.45
     residuos
    0.45
    ্ক
    0.44
    時間の
    0.43
     washing
    0.43
     vzh
    0.42
     statement
    0.42
     molestias
    0.41
    ल
    0.41
    Activations Density 0.000%

    No Known Activations