© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 80691
    Prev
    Next
    INDEX
    Explanations

    puts something at risk

    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
    い
    1.51
    ή
    1.48
    ü
    1.38
    .
    1.36
    ड
    1.34
    ك
    1.31
    ת
    1.27
     you
    1.27
     with
    1.25
    한
    1.21
    POSITIVE LOGITS
    UL
    1.62
    '
    1.59
    的选择
    1.49
    nThe
    1.41
    nCurrent
    1.36
    の後
    1.33
    s
    1.27
    :
    1.27
     Владимир
    1.25
    ে
    1.25
    Activations Density 0.001%

    No Known Activations