© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139312
    Prev
    Next
    INDEX
    Explanations

    AI models and services

    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_12_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
    t
    0.71
    s
    0.68
    en
    0.65
    ai
    0.64
    i
    0.63
    us
    0.63
    set
    0.63
    se
    0.59
    is
    0.58
    d
    0.57
    POSITIVE LOGITS
     ايجاد
    0.62
    之时
    0.58
    :
    0.53
     것도
    0.52
     사례
    0.52
     paragraph
    0.50
     Paragraph
    0.49
    👗
    0.49
     retaliation
    0.48
     exemplary
    0.47
    Activations Density 0.011%

    No Known Activations