© 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
    2. Gemma-3-27B-IT
    3. 60-GEMMASCOPE-2-TRANSCODER-262K
    4. 90455
    Prev
    Next
    INDEX
    Explanations

    toxic

    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_60_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
    /-
    0.44
     ima
    0.44
    itoti
    0.44
    ongen
    0.42
     Agen
    0.41
     larc
    0.40
    Agence
    0.39
     ado
    0.39
    -(-
    0.39
     imate
    0.38
    POSITIVE LOGITS
    t
    0.46
    简单的
    0.41
    city
    0.39
     regarded
    0.38
    白的
    0.38
     strong
    0.38
    اسية
    0.37
    H
    0.36
    City
    0.35
    JV
    0.35
    Activations Density 0.001%

    No Known Activations