© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83052
    Prev
    Next
    INDEX
    Explanations

    coordinated actions

    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
    нов
    1.52
    ین
    1.45
    ма
    1.38
    ين
    1.27
    ی
    1.25
    鶘
    1.25
    ā
    1.24
     بیاکت
    1.23
     перспек
    1.21
    trashItem
    1.20
    POSITIVE LOGITS
    ↵↵
    1.77
    '
    1.64
    ↵
    1.46
     for
    1.41
     at
    1.41
    ำ
    1.40
    0
    1.37
    ால்
    1.36
    ’
    1.33
    3
    1.27
    Activations Density 0.000%

    No Known Activations