© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96766
    Prev
    Next
    INDEX
    Explanations

    drug abuse

    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_14_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
     znač
    0.52
    ות
    0.49
     ljud
    0.48
    ط
    0.47
     Y
    0.47
    ᓪ
    0.45
     lawyers
    0.45
     dix
    0.45
    ح
    0.45
     profes
    0.45
    POSITIVE LOGITS
    кість
    0.54
     மாறிய
    0.53
     о
    0.52
    ését
    0.50
     уч
    0.49
     cò
    0.49
     máu
    0.48
    couch
    0.48
    ｂ
    0.47
    coating
    0.47
    Activations Density 0.002%

    No Known Activations