© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85734
    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_23_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
    array
    0.40
    see
    0.37
     بأ
    0.37
    )$$
    0.37
    गत
    0.36
    tree
    0.35
    Last
    0.35
    ologische
    0.35
    TEX
    0.35
    SPREAD
    0.34
    POSITIVE LOGITS
     metros
    0.43
    쾨
    0.43
     deliverables
    0.43
     flyers
    0.43
     кер
    0.43
     fulfills
    0.42
     technicians
    0.42
     équipes
    0.41
     versatility
    0.41
     fulfilling
    0.40
    Activations Density 0.000%

    No Known Activations