© 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. 35787
    Prev
    Next
    INDEX
    Explanations

    base64 encoded image data

    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
     drücken
    0.41
     Weing
    0.39
     drugstore
    0.38
    сад
    0.36
    吕
    0.36
     hue
    0.36
    RGB
    0.35
     noss
    0.35
     phenotype
    0.35
     delineate
    0.35
    POSITIVE LOGITS
     във
    0.38
     particulières
    0.37
    贯
    0.36
    এর
    0.36
    工作的
    0.36
     ঘন্টার
    0.35
    醒
    0.35
    )),
    0.35
     მე
    0.35
    columns
    0.34
    Activations Density 0.002%

    No Known Activations