© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170945
    Prev
    Next
    INDEX
    Explanations

    plotting commands and visualization

    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_20_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
    Ə
    0.46
    ))));
    0.43
     الإ
    0.42
    هرة
    0.40
     револю
    0.40
    ә
    0.39
    гістра
    0.38
    ُل
    0.38
    に対
    0.37
    らせ
    0.37
    POSITIVE LOGITS
    nist
    0.49
     jinfo
    0.48
    ycles
    0.47
     zy
    0.46
     gekauft
    0.46
    ренный
    0.46
    gett
    0.45
     goede
    0.45
    κης
    0.45
     good
    0.44
    Activations Density 0.000%

    No Known Activations