© 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. 112129
    Prev
    Next
    INDEX
    Explanations

    earrings

    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
    د
    1.53
     ऑन
    1.30
    この
    1.21
    д
    1.19
    Untuk
    1.13
    ری
    1.13
    $)$.
    1.12
    見
    1.10
    ال
    1.09
     вещей
    1.09
    POSITIVE LOGITS
    n
    1.84
    ר
    1.55
     A
    1.49
    in
    1.47
    ar
    1.47
     K
    1.45
     W
    1.42
     U
    1.40
    il
    1.38
     V
    1.38
    Activations Density 0.001%

    No Known Activations