© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7105
    Prev
    Next
    INDEX
    Explanations

    Emperor proclaims

    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_40_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
    dürü
    0.39
    入射
    0.37
    취
    0.36
     நடவடிக்கை
    0.36
     abrasion
    0.35
     случа
    0.35
     dispose
    0.35
    latent
    0.35
    udni
    0.35
    到时候
    0.35
    POSITIVE LOGITS
     Empire
    0.50
    Empire
    0.48
     empire
    0.41
     proclam
    0.40
     empires
    0.39
    Imperial
    0.39
    ᱪ
    0.37
     Empires
    0.37
     monthly
    0.37
     proclamation
    0.36
    Activations Density 0.025%

    No Known Activations