© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 157533
    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_50_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
     m
    0.47
     Med
    0.44
    ₆
    0.39
     pi
    0.38
     drizzle
    0.38
     Blum
    0.37
    ¼
    0.37
     child
    0.37
     pillars
    0.37
     Méd
    0.37
    POSITIVE LOGITS
    ্সে
    0.44
    CON
    0.42
     কথোপকথ
    0.42
     பயன்ப
    0.41
    CONH
    0.41
    Opportun
    0.40
    JSPA
    0.40
    Prosecutors
    0.39
    菪
    0.38
    ότερα
    0.38
    Activations Density 0.000%

    No Known Activations