© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180796
    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_24_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
    قر
    0.49
    orse
    0.44
     infine
    0.43
    èces
    0.42
    مس
    0.42
    de
    0.41
     وز
    0.40
    ب
    0.40
    ähr
    0.39
     seized
    0.39
    POSITIVE LOGITS
     boyfriend
    0.51
    ед
    0.51
    өрд
    0.50
    ↕
    0.47
     varsity
    0.46
    Y
    0.45
     beanie
    0.45
    _{+}\
    0.44
     করিয়াছে
    0.44
     CHD
    0.44
    Activations Density 0.000%

    No Known Activations