© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250588
    Prev
    Next
    INDEX
    Explanations

    Signed off changes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Building
    0.45
     Использу
    0.43
     kilobytes
    0.39
     Bug
    0.39
     P
    0.38
     Comment
    0.37
     Added
    0.37
    ‐
    0.37
     building
    0.37
     dibangun
    0.37
    POSITIVE LOGITS
     signed
    0.56
    Signed
    0.51
    SIGNED
    0.48
    signed
    0.48
     подписа
    0.46
    Clean
    0.44
     clean
    0.44
     LUMPUR
    0.43
    簽
    0.39
    Passed
    0.39
    Activations Density 0.000%

    No Known Activations