© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54349
    Prev
    Next
    INDEX
    Explanations

    states starting with A or Ar

    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_30_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
    ടാ
    0.37
     tangga
    0.36
    gaxModule
    0.35
    enumerate
    0.34
    鍔
    0.34
    ondo
    0.34
     peregr
    0.34
     enkele
    0.34
     endanger
    0.34
     താഴ
    0.33
    POSITIVE LOGITS
     Warden
    0.42
    იკ
    0.40
    뻘
    0.40
     agents
    0.38
    啊
    0.36
     blurring
    0.36
    Audio
    0.35
     amperes
    0.35
     contratto
    0.35
     arque
    0.34
    Activations Density 0.002%

    No Known Activations