© 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. 3770
    Prev
    Next
    INDEX
    Explanations

    lean protein sources, spring beans

    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
     প্রদর্শ
    0.45
     ayudas
    0.43
    ablus
    0.40
     Nightingale
    0.39
    ROME
    0.38
    
    0.38
    angu
    0.37
     activates
    0.36
    取材
    0.36
     tarjetas
    0.36
    POSITIVE LOGITS
    呛
    0.38
    ʒ
    0.37
    pole
    0.37
     வினை
    0.36
    ержа
    0.35
     ቤት
    0.35
     ≈
    0.35
     longiore
    0.35
    Buddy
    0.34
     Merrick
    0.34
    Activations Density 0.000%

    No Known Activations