© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141337
    Prev
    Next
    INDEX
    Explanations

    thematicanalysisandcoding

    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_12_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
    nosti
    0.51
    vä
    0.48
     భాగంగా
    0.48
    äder
    0.46
    vät
    0.46
     suure
    0.46
    攵
    0.46
    
    0.45
    disturbance
    0.44
     одно
    0.43
    POSITIVE LOGITS
     carpets
    0.68
     carpet
    0.64
     scaff
    0.58
     try
    0.56
     credits
    0.54
     by
    0.51
     scallops
    0.51
     খেল
    0.51
     bungalows
    0.51
     prefers
    0.50
    Activations Density 0.001%

    No Known Activations