© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60884
    Prev
    Next
    INDEX
    Explanations

    tobacco

    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_59_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
    o
    1.31
    re
    0.89
    oer
    0.55
    oC
    0.54
    ו
    0.53
     ре
    0.50
    oğlu
    0.47
    ra
    0.46
    b
    0.46
    芭
    0.43
    POSITIVE LOGITS
    al
    0.53
    cd
    0.50
    ală
    0.44
    alt
    0.42
    agility
    0.42
    alh
    0.42
    alop
    0.41
    alos
    0.41
    alous
    0.41
    ัล
    0.41
    Activations Density 0.001%

    No Known Activations