© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140001
    Prev
    Next
    INDEX
    Explanations

    say "lip"

    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_46_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
     Gaspar
    0.42
     doGet
    0.40
    ╬
    0.39
     EDC
    0.38
     Physique
    0.38
    BERG
    0.37
     গ্যাস
    0.36
    dT
    0.36
     Sare
    0.36
     introspection
    0.36
    POSITIVE LOGITS
     mouth
    0.80
     lip
    0.69
     lips
    0.64
     Mouth
    0.64
    口
    0.62
     mouths
    0.59
     Lip
    0.57
    mouth
    0.55
     boca
    0.55
     miệng
    0.55
    Activations Density 0.004%

    No Known Activations