© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90059
    Prev
    Next
    INDEX
    Explanations

    help the user

    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_60_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
     बखूबी
    0.43
    都有
    0.43
     mohou
    0.40
     nettement
    0.40
    ዷ
    0.40
     확인할
    0.39
    ასი
    0.38
     mogą
    0.38
    阠
    0.37
    队
    0.37
    POSITIVE LOGITS
     Am
    0.60
     more
    0.54
     am
    0.53
     match
    0.52
     K
    0.49
     Known
    0.48
    Am
    0.48
     suits
    0.47
     for
    0.45
     react
    0.44
    Activations Density 0.003%

    No Known Activations