© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230150
    Prev
    Next
    INDEX
    Explanations

    Spring `Bean` definitions

    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_6_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
     as
    1.10
    '
    1.03
    ની
    0.86
     conex
    0.76
    时
    0.76
     creek
    0.74
     guise
    0.74
    公司
    0.73
     再
    0.73
    无奈
    0.72
    POSITIVE LOGITS
    ש
    1.05
    int
    0.88
    il
    0.85
    ח
    0.84
    ین
    0.82
    ik
    0.81
    К
    0.81
    in
    0.80
    ilung
    0.78
    க
    0.78
    Activations Density 0.000%

    No Known Activations