© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28413
    Prev
    Next
    INDEX
    Explanations

    inside/outside boundaries

    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_10_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
    ر
    0.77
    C
    0.71
    ু
    0.65
    Inser
    0.61
    יי
    0.61
    returns
    0.61
     Schnitt
    0.61
    └
    0.61
    מו
    0.60
    р
    0.60
    POSITIVE LOGITS
    able
    0.71
     outside
    0.70
     extérieur
    0.67
     antiserum
    0.63
     extérieure
    0.61
     aquaculture
    0.61
     exteriores
    0.61
    erving
    0.60
    外的
    0.60
     intérieure
    0.60
    Activations Density 0.032%

    No Known Activations