© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22325
    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_56_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
     ‎
    0.42
     njegov
    0.42
     “
    0.42
    ორის
    0.41
     njen
    0.40
     ‌
    0.40
     его
    0.40
    उनके
    0.40
    他的
    0.39
    ުގެ
    0.38
    POSITIVE LOGITS
    ’
    1.06
    '
    0.91
    ＇
    0.81
    ’
    0.78
    ׳
    0.73
    ´
    0.71
    \'
    0.70
    ʼ
    0.70
    ᾽
    0.69
    ‟
    0.69
    Activations Density 0.000%

    No Known Activations