© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234796
    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
    CERT
    0.40
     Bc
    0.39
    忄
    0.38
    Перед
    0.38
    Sockets
    0.38
     CERT
    0.38
    cert
    0.37
    Bc
    0.37
    বর্তমান
    0.37
    Rew
    0.37
    POSITIVE LOGITS
    ꉂ
    0.39
     natively
    0.38
    رق
    0.37
    갚
    0.36
     innate
    0.36
    readyState
    0.36
     دوا
    0.35
     infiltrating
    0.34
     செல்க
    0.34
     softness
    0.33
    Activations Density 0.000%

    No Known Activations