© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196211
    Prev
    Next
    INDEX
    Explanations

    pride

    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
     navigation
    0.42
     nuôi
    0.41
    navigation
    0.41
    нави
    0.40
    curité
    0.40
    养
    0.39
    onavirus
    0.38
     cultivation
    0.38
     nourishment
    0.38
     nourished
    0.37
    POSITIVE LOGITS
     unsc
    0.38
    撅
    0.38
     Group
    0.38
    GroupID
    0.38
    ydney
    0.37
    Boards
    0.36
     Groups
    0.36
     Gruppen
    0.36
    groupID
    0.36
     group
    0.35
    Activations Density 0.001%

    No Known Activations