© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60770
    Prev
    Next
    INDEX
    Explanations

    awk command

    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_11_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
     apology
    0.44
     şeyler
    0.43
     የ
    0.43
     disclaimer
    0.41
    Divine
    0.40
     skipping
    0.40
     aton
    0.39
     behaves
    0.39
     natively
    0.39
    Fate
    0.39
    POSITIVE LOGITS
     Beit
    0.41
     CtApp
    0.41
    ,-\
    0.40
     Reb
    0.39
     अब्
    0.39
    -)
    0.38
     Sloven
    0.38
    )».
    0.38
    marginBottom
    0.38
    温暖
    0.38
    Activations Density 0.020%

    No Known Activations