© 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. 112288
    Prev
    Next
    INDEX
    Explanations

    pump or AMP

    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
    ل
    1.73
    ي
    1.48
    ।
    1.45
    。
    1.34
    ש
    1.30
    ла
    1.27
     is
    1.26
    י
    1.23
    ัน
    1.21
    ार
    1.20
    POSITIVE LOGITS
    for
    1.14
     be
    1.07
    didReceive
    1.03
     for
    1.01
    Y
    1.01
    ка
    1.00
    M
    0.98
    difficulty
    0.96
     feme
    0.95
    MAKE
    0.93
    Activations Density 0.004%

    No Known Activations