© 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. 253138
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
     ा
    0.62
     க்கு
    0.49
     )[
    0.47
     eind
    0.46
     )(
    0.45
     dto
    0.44
     dhan
    0.43
     nd
    0.43
     शी
    0.41
     ,'
    0.41
    POSITIVE LOGITS
    oting
    0.36
    利
    0.35
    ë
    0.34
    лін
    0.34
    nění
    0.34
    —
    0.34
    MISSIONS
    0.32
    🏿
    0.32
    õi
    0.32
    lint
    0.32
    Activations Density 0.134%

    No Known Activations