© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108886
    Prev
    Next
    INDEX
    Explanations

    ESOP creation

    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
     in
    1.56
    在
    1.36
    야
    1.26
    жи
    1.09
    에요
    1.06
    ใน
    0.99
    اری
    0.99
    ви
    0.98
    .
    0.98
    ように
    0.94
    POSITIVE LOGITS
    G
    1.41
    ية
    1.29
    B
    1.26
    ist
    1.20
    om
    1.20
    F
    1.18
    কে
    1.17
    p
    1.17
    W
    1.17
    the
    1.16
    Activations Density 0.000%

    No Known Activations