© 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. 62340
    Prev
    Next
    INDEX
    Explanations

    AAAA pattern

    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
    s
    1.64
    I
    1.63
    و
    1.53
    (
    1.50
    i
    1.42
    ка
    1.37
    కు
    1.27
    在
    1.27
    is
    1.24
    B
    1.23
    POSITIVE LOGITS
     for
    1.51
     from
    1.05
    ז
    1.05
    ES
    1.03
     ollut
    1.03
     et
    1.02
     injuring
    0.96
     Một
    0.96
     것처럼
    0.96
     been
    0.94
    Activations Density 0.000%

    No Known Activations