© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5134
    Prev
    Next
    INDEX
    Explanations

    produce and plant parts

    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
    ンテージ
    0.40
     もの
    0.37
    서비스
    0.35
    hla
    0.35
    佗
    0.35
     एलिमेंट
    0.34
    匡
    0.34
    다고
    0.34
     amacı
    0.34
     પ્રકાર
    0.33
    POSITIVE LOGITS
    잎
    0.44
     stalks
    0.43
     husk
    0.43
     shavings
    0.43
     প্রতী
    0.43
     tuber
    0.42
     picker
    0.41
    çay
    0.40
    籽
    0.40
     yellows
    0.40
    Activations Density 0.200%

    No Known Activations