© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45717
    Prev
    Next
    INDEX
    Explanations

    in that [clause explaining similarity/definition]

    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_13_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
    )+\
    0.65
    노
    0.61
    )-\
    0.58
    錒
    0.58
    ෲ
    0.57
    សូម
    0.57
     sizi
    0.57
     millió
    0.56
     وزير
    0.55
    પતિ
    0.55
    POSITIVE LOGITS
    d
    0.70
    </h3>
    0.61
     D
    0.61
     '
    0.59
    :
    0.57
     DEL
    0.53
     t
    0.52
    ico
    0.52
    éra
    0.52
    t
    0.52
    Activations Density 0.002%

    No Known Activations