© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6343
    Prev
    Next
    INDEX
    Explanations

    information schema

    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_40_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
     வரி
    0.40
    apsack
    0.39
    枯
    0.37
    mniejs
    0.36
    無
    0.36
    بيه
    0.35
    ásico
    0.34
    kapal
    0.34
    緩
    0.34
     Flowering
    0.34
    POSITIVE LOGITS
     Nun
    0.48
    xlim
    0.39
     nun
    0.39
     വീ
    0.38
     kel
    0.37
    𝑃
    0.37
     Possible
    0.37
     nuns
    0.37
     נפ
    0.36
     ને
    0.35
    Activations Density 0.009%

    No Known Activations