© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39412
    Prev
    Next
    INDEX
    Explanations

    detect defects or malfunctions

    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_11_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
    Ζ
    0.45
    Ύ
    0.42
    プラス
    0.41
    Έ
    0.39
    Luego
    0.38
    said
    0.37
    ंतर
    0.37
    Ε
    0.37
     pisos
    0.36
    saus
    0.36
    POSITIVE LOGITS
     obnoxious
    0.47
     atrocious
    0.43
     awkward
    0.40
     ridiculous
    0.39
     oaks
    0.38
     mammals
    0.38
     റോ
    0.38
     gravel
    0.38
    μων
    0.38
    哞
    0.37
    Activations Density 0.051%

    No Known Activations