© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6016
    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_39_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
     ইং
    0.38
     الاك
    0.33
    工作
    0.33
    Arms
    0.33
     inhab
    0.32
    ドン
    0.32
    LAW
    0.32
    𝘯
    0.31
    經驗
    0.31
    édon
    0.31
    POSITIVE LOGITS
    CLUSIVE
    0.42
     Transforms
    0.41
     seeds
    0.40
     Hr
    0.38
     نم
    0.36
     Fb
    0.36
     ALLE
    0.36
     transformative
    0.35
     atmospheric
    0.35
     fiscales
    0.34
    Activations Density 0.004%

    No Known Activations