© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59130
    Prev
    Next
    INDEX
    Explanations

    an followed by 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_2_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
    on
    1.07
    ৫
    1.05
    ло
    1.03
    h
    1.02
    2
    1.02
    ت
    1.02
    തി
    1.02
     lleg
    1.02
     thiab
    1.00
    8
    1.00
    POSITIVE LOGITS
    ↵
    1.70
     an
    1.41
    -
    1.05
    ،
    1.02
     to
    1.01
    ka
    1.00
    )
    0.98
    ).
    0.93
    kaan
    0.91
    va
    0.91
    Activations Density 0.003%

    No Known Activations