© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30828
    Prev
    Next
    INDEX
    Explanations

    dorsal stripe

    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_31_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
    🏇
    0.50
     riding
    0.48
     rode
    0.46
    骑
    0.45
     riders
    0.42
     Riding
    0.41
     saddle
    0.41
    rode
    0.40
    riding
    0.40
     saddles
    0.38
    POSITIVE LOGITS
     Cardiac
    0.38
    ᆷ
    0.37
    鏡
    0.36
     conditional
    0.36
     mangiare
    0.35
    рил
    0.35
    <unused30>
    0.35
     Serb
    0.34
     healthy
    0.34
    វា
    0.34
    Activations Density 0.034%

    No Known Activations