© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12983
    Prev
    Next
    INDEX
    Explanations

    Navigating finance and data systems

    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_13_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
     النج
    0.53
    lobe
    0.50
    hod
    0.49
    loft
    0.49
    Lbl
    0.49
    Online
    0.48
    婼
    0.48
    sele
    0.47
    zków
    0.47
    Bau
    0.46
    POSITIVE LOGITS
     whose
    0.52
     ier
    0.49
     н
    0.48
     Whose
    0.47
     muit
    0.46
     PCM
    0.46
     byen
    0.46
     psychosis
    0.46
     (...)
    0.45
     яв
    0.45
    Activations Density 0.020%

    No Known Activations