© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132848
    Prev
    Next
    INDEX
    Explanations

    extra

    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_50_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
    मक
    0.39
    routeProvider
    0.38
    ресень
    0.38
    萋
    0.37
    ったり
    0.36
     bầu
    0.36
    ریح
    0.34
    畋
    0.34
    ouses
    0.33
    드렸
    0.33
    POSITIVE LOGITS
     extra
    3.83
    extra
    3.42
     Extra
    3.34
    Extra
    3.31
     ekstra
    3.17
     EXTRA
    2.95
    EXTRA
    2.84
    额外
    2.19
     अतिरिक्त
    2.02
     extras
    1.98
    Activations Density 0.005%

    No Known Activations