© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166925
    Prev
    Next
    INDEX
    Explanations

    ASCII art structures

    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_34_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
     sig
    0.42
    its
    0.37
     arac
    0.37
    其
    0.36
     foy
    0.35
     cub
    0.34
    ris
    0.34
    zie
    0.34
     its
    0.34
     ely
    0.33
    POSITIVE LOGITS
    渾
    0.38
    协商
    0.36
    촬
    0.36
    蛸
    0.34
    Infof
    0.34
    絘
    0.34
    教育
    0.34
    優勝
    0.34
    Respect
    0.33
     rispetto
    0.33
    Activations Density 0.001%

    No Known Activations