© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210544
    Prev
    Next
    INDEX
    Explanations

    dry

    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_43_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
    นี
    0.43
    jacoco
    0.38
    PTR
    0.36
     خز
    0.36
    繳
    0.36
    颅
    0.35
    ኘት
    0.35
    byterian
    0.34
    photon
    0.34
    JsonObject
    0.34
    POSITIVE LOGITS
     dry
    0.81
    Dry
    0.79
     Dry
    0.78
     ड्राई
    0.77
    dry
    0.73
     DRY
    0.70
     kering
    0.64
    乾
    0.61
    干
    0.56
     dryness
    0.54
    Activations Density 0.000%

    No Known Activations