© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201687
    Prev
    Next
    INDEX
    Explanations

    interface definitions

    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
     analysing
    0.60
    ਨ
    0.60
     पार्ट
    0.59
     चम्म
    0.58
     Analyses
    0.58
     கம
    0.58
     probablemente
    0.57
     ponerse
    0.57
     analizar
    0.56
    n
    0.55
    POSITIVE LOGITS
    0
    0.56
    android
    0.55
    City
    0.51
    Among
    0.50
     priority
    0.50
     sisters
    0.50
    ług
    0.49
     long
    0.49
    richtung
    0.49
    3
    0.48
    Activations Density 0.000%

    No Known Activations