© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31156
    Prev
    Next
    INDEX
    Explanations

    fly, income, property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     Bar
    0.39
     Tre
    0.38
     Function
    0.38
    THANK
    0.38
    optical
    0.38
    국
    0.38
     Barley
    0.37
     тре
    0.37
    Sch
    0.37
     doua
    0.36
    POSITIVE LOGITS
     wan
    0.38
    锥
    0.34
    ]$;
    0.34
    熹
    0.34
     ag
    0.33
     ike
    0.33
    ނ
    0.33
     hog
    0.33
     jl
    0.33
     catechol
    0.32
    Activations Density 0.046%

    No Known Activations