© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3304
    Prev
    Next
    INDEX
    Explanations

    A followed by descriptive words

    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_39_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
    ');//
    0.38
     sensitivity
    0.37
     inputs
    0.37
    ',$
    0.36
     Sensitivity
    0.35
    👏👏👏👏
    0.35
    龊
    0.35
    INPUT
    0.35
    篒
    0.35
     vulnerability
    0.35
    POSITIVE LOGITS
     Clo
    0.41
     skú
    0.41
    琹
    0.39
    linde
    0.37
     sicht
    0.36
     jin
    0.35
     fullness
    0.35
     চতু
    0.35
     Zusätzlich
    0.35
     স্পষ্টভাবে
    0.34
    Activations Density 0.113%

    No Known Activations