© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197186
    Prev
    Next
    INDEX
    Explanations

    fasteners and components

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    2.27
     М
    1.62
     الم
    1.41
    M
    1.30
     एम
    1.28
    Ｍ
    1.24
    М
    1.02
     এম
    0.98
     Μ
    0.96
    𝑀
    0.95
    POSITIVE LOGITS
    middleware
    0.40
    მე
    0.39
    minded
    0.39
     Tax
    0.38
     THF
    0.38
     TPS
    0.37
    ToSend
    0.37
     प्रोटो
    0.37
    TPS
    0.37
    STS
    0.36
    Activations Density 0.010%

    No Known Activations