© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16326
    Prev
    Next
    INDEX
    Explanations

    drug abuse, possessing

    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_40_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
    Absent
    0.44
    वाणी
    0.41
    ┓
    0.41
    🧚
    0.40
    bigcirc
    0.40
     clarified
    0.39
    textbackslash
    0.38
     CAM
    0.37
    㧔
    0.37
    Fury
    0.37
    POSITIVE LOGITS
    lden
    0.39
     Bir
    0.38
    poses
    0.35
     bir
    0.35
    Bir
    0.35
    有好
    0.34
     filede
    0.34
    note
    0.34
     Lionel
    0.34
    bibliothek
    0.34
    Activations Density 0.023%

    No Known Activations