© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83209
    Prev
    Next
    INDEX
    Explanations

    With [years/background/context]

    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_29_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
     얼마
    0.38
     grade
    0.37
     many
    0.37
     laver
    0.37
    钙
    0.36
    プリング
    0.35
    ⎪
    0.35
    تل
    0.35
    니
    0.34
    滯
    0.34
    POSITIVE LOGITS
     entrevista
    0.41
    )}_{
    0.40
    雳
    0.39
    )^{(
    0.39
    奀
    0.38
     tekrar
    0.38
    LOTREntity
    0.38
    ]==
    0.37
     allemaal
    0.37
    Então
    0.37
    Activations Density 0.001%

    No Known Activations