© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232550
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_32_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
    لیسی
    0.39
     WindowStateType
    0.38
    騰
    0.37
     giữa
    0.36
    Denne
    0.36
     ótimo
    0.36
     sporty
    0.35
    ແ
    0.35
    鋼
    0.35
    চী
    0.35
    POSITIVE LOGITS
    izes
    0.46
    ized
    0.40
    izable
    0.39
     rabbits
    0.36
    /-/
    0.35
     indicates
    0.34
     bursts
    0.34
     address
    0.34
     interpretations
    0.34
     rabbit
    0.33
    Activations Density 0.004%

    No Known Activations