© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20079
    Prev
    Next
    INDEX
    Explanations

    Times

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     times
    0.45
     Times
    0.45
    ᅯ
    0.40
    환경
    0.40
    ／
    0.40
    usega
    0.39
    Times
    0.38
    ус
    0.37
    ӡ
    0.37
     effusion
    0.37
    POSITIVE LOGITS
     Nueva
    0.54
     New
    0.53
    Nueva
    0.52
    New
    0.50
     NEW
    0.50
    liv
    0.49
    lid
    0.44
    NEW
    0.44
    न्यू
    0.42
     нового
    0.42
    Activations Density 0.001%

    No Known Activations