© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226466
    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_10_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
    quet
    0.50
    莓
    0.49
    ar
    0.47
     जबकि
    0.47
    prar
    0.46
     جبکہ
    0.46
    Transcription
    0.46
    ๐
    0.46
     memoria
    0.45
    Course
    0.45
    POSITIVE LOGITS
     ample
    0.53
     disregarded
    0.52
     amplified
    0.49
    のうち
    0.48
     overestimated
    0.48
     cheated
    0.47
     disappointed
    0.47
     obliterated
    0.46
     phones
    0.46
     urgently
    0.46
    Activations Density 0.000%

    No Known Activations