© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7110
    Prev
    Next
    INDEX
    Explanations

    statistical questions and distributions

    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_39_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
     segunda
    0.42
    engineer
    0.38
     Wärm
    0.37
     sepen
    0.37
     ink
    0.35
     second
    0.35
     DECL
    0.35
    ˏ
    0.34
     layered
    0.34
     thermally
    0.34
    POSITIVE LOGITS
    素
    0.40
    indrical
    0.38
    brar
    0.38
    USA
    0.36
    微笑
    0.36
    ({'
    0.35
     Anybody
    0.35
     gavel
    0.34
     amar
    0.34
    azim
    0.33
    Activations Density 0.034%

    No Known Activations