© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 148414
    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_59_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
     также
    0.40
    también
    0.38
     Men
    0.37
    亦
    0.36
    convén
    0.36
     దగ్
    0.36
    frau
    0.36
    们
    0.36
    ാനും
    0.35
    разде
    0.35
    POSITIVE LOGITS
     ref
    0.59
     pour
    0.45
     st
    0.45
     rif
    0.44
    Ref
    0.41
     Pour
    0.41
    ref
    0.40
    getSt
    0.39
     על
    0.39
    pour
    0.39
    Activations Density 0.000%

    No Known Activations