© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133197
    Prev
    Next
    INDEX
    Explanations

    food or cuisine

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     baht
    0.55
    baidu
    0.49
    Golem
    0.45
    ba
    0.44
    Ba
    0.43
     ba
    0.42
    Baj
    0.42
     T
    0.41
    Chap
    0.41
    T
    0.41
    POSITIVE LOGITS
     Pitt
    0.45
     pitches
    0.41
     hamb
    0.40
     Colchester
    0.39
     cold
    0.39
     noodles
    0.38
    potent
    0.38
     coolers
    0.38
    pidos
    0.37
     kalam
    0.37
    Activations Density 0.019%

    No Known Activations