© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32846
    Prev
    Next
    INDEX
    Explanations

    i.e. punctuation

    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_7_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
    1.25
    and
    1.14
     a
    1.02
     and
    0.96
     for
    0.92
    O
    0.91
    ok
    0.90
    2
    0.90
    elling
    0.86
     was
    0.86
    POSITIVE LOGITS
    들이
    1.12
    ۔
    1.03
    IRCONIUM
    0.90
    س
    0.89
    нің
    0.88
    с
    0.86
    ز
    0.84
    នៅ
    0.79
    getBlueTeam
    0.77
    ವನ್ನು
    0.75
    Activations Density 0.001%

    No Known Activations