© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144724
    Prev
    Next
    INDEX
    Explanations

    concentration

    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_0_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
    1
    1.81
    ing
    1.80
    2
    1.77
    M
    1.70
    S
    1.63
    E
    1.63
    G
    1.60
    IT
    1.59
    D
    1.59
     for
    1.53
    POSITIVE LOGITS
    ের
    1.29
    би
    1.27
    ς
    1.26
     an
    1.24
    numOf
    1.23
    ров
    1.22
    ی
    1.20
    myLabels
    1.19
    ру
    1.16
     மிக
    1.16
    Activations Density 0.001%

    No Known Activations