© 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. 21013
    Prev
    Next
    INDEX
    Explanations

    opening parenthesis

    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_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
    ቿ
    0.39
     tubercle
    0.38
     договора
    0.38
     حق
    0.37
    ﹉
    0.37
     tongue
    0.37
     داد
    0.37
    舌
    0.36
     Hirsch
    0.36
     Vertrag
    0.36
    POSITIVE LOGITS
     nx
    1.10
     NX
    1.09
     Nx
    1.06
    NX
    1.03
    nx
    1.00
     nt
    0.96
     Nt
    0.96
     NT
    0.96
    NT
    0.95
    Nx
    0.95
    Activations Density 0.067%

    No Known Activations