© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213566
    Prev
    Next
    INDEX
    Explanations

    juice

    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_47_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
     thick
    1.25
    thick
    1.19
     Thick
    1.10
     thicker
    1.09
     thickness
    1.09
    厚
    1.07
     Thickness
    1.04
    thickness
    1.01
    Thickness
    0.95
     thicknesses
    0.94
    POSITIVE LOGITS
     juice
    1.40
     Juice
    1.30
    juice
    1.21
     juices
    1.18
     जूस
    0.98
    Ju
    0.97
     ju
    0.96
     juicy
    0.95
     JU
    0.94
    汁
    0.91
    Activations Density 0.000%

    No Known Activations