© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110268
    Prev
    Next
    INDEX
    Explanations

    network of

    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_2_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
    T
    2.09
    D
    1.88
    R
    1.88
    S
    1.71
    M
    1.66
    W
    1.66
    H
    1.65
    P
    1.58
    Y
    1.54
    G
    1.49
    POSITIVE LOGITS
    s
    1.48
    ים
    1.34
    ς
    1.28
    ی
    1.26
    ੀ
    1.12
    ان
    1.05
    их
    1.05
    ের
    1.02
    های
    1.02
     reasoned
    1.00
    Activations Density 0.002%

    No Known Activations