© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132545
    Prev
    Next
    INDEX
    Explanations

    cellphone

    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_1_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
    a
    2.33
    A
    1.54
    o
    1.37
    ס
    1.36
    ه
    1.34
    া
    1.32
    I
    1.23
    ق
    1.18
    u
    1.16
    is
    1.10
    POSITIVE LOGITS
    '
    1.16
    rokken
    0.83
    ında
    0.80
    ong
    0.79
    vorm
    0.79
    erna
    0.78
    一流
    0.77
    scapes
    0.76
    engen
    0.76
    ibr
    0.75
    Activations Density 0.000%

    No Known Activations