© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53369
    Prev
    Next
    INDEX
    Explanations

    I am programmed

    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_55_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
     broader
    0.52
     broad
    0.47
     широкий
    0.39
     viscosity
    0.39
     +'
    0.39
     Pelt
    0.38
     कामगिरी
    0.38
     breadth
    0.38
     широ
    0.38
     monthly
    0.37
    POSITIVE LOGITS
     refined
    0.38
    égio
    0.38
    con
    0.38
    raff
    0.38
    cols
    0.37
    yler
    0.37
    urz
    0.36
     ফ
    0.36
    ленная
    0.36
    streams
    0.35
    Activations Density 0.000%

    No Known Activations