© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165247
    Prev
    Next
    INDEX
    Explanations

    moisture, damp, wetness

    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
    开放
    0.40
    Open
    0.39
    Frost
    0.38
     ओपन
    0.37
    🚥
    0.36
     open
    0.35
     Open
    0.35
     OPEN
    0.35
     ouverte
    0.35
    鸵
    0.35
    POSITIVE LOGITS
    土壤
    0.50
     ഭക്ഷണം
    0.48
     soil
    0.47
     comidas
    0.46
     کھانا
    0.45
     пищи
    0.44
     土
    0.43
     kisses
    0.43
     towels
    0.42
    ധാ
    0.41
    Activations Density 0.039%

    No Known Activations