© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67580
    Prev
    Next
    INDEX
    Explanations

    public

    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_51_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
     mud
    1.69
     Mud
    1.55
    Mud
    1.55
    mud
    1.51
    泥
    1.24
     muddy
    1.11
     mudd
    0.81
     Mudd
    0.81
     dirt
    0.78
     mudar
    0.77
    POSITIVE LOGITS
     Public
    0.58
     públicos
    0.56
     public
    0.55
    public
    0.54
     öffentlichen
    0.54
    Public
    0.50
    公
    0.49
     öffentliche
    0.49
     pubblico
    0.48
     सार्वजनिक
    0.48
    Activations Density 0.018%

    No Known Activations