© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133302
    Prev
    Next
    INDEX
    Explanations

    truly tremendous

    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
    I
    1.70
    .
    1.68
    -.
    1.18
    ¹.
    1.18
    ।
    1.17
    2
    1.13
    __.
    1.13
    '.
    1.05
    0
    1.04
    !
    1.03
    POSITIVE LOGITS
    с
    1.41
    д
    1.07
    ého
    1.05
    이니까
    1.04
     đám
    1.03
    ем
    0.99
    ul
    0.96
     can
    0.96
    ด
    0.94
     څر
    0.94
    Activations Density 0.000%

    No Known Activations