© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50965
    Prev
    Next
    INDEX
    Explanations

    a followed by punctuation

    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
    चारिक
    0.41
    atação
    0.40
     ContentView
    0.40
     कंडक्टर
    0.38
     dây
    0.36
     Doors
    0.36
     हराकर
    0.35
    ս
    0.35
    就是在
    0.35
     दिग्विजय
    0.35
    POSITIVE LOGITS
     sucks
    0.41
     নিম
    0.40
    ម្ម
    0.38
    ρων
    0.38
     doesn
    0.38
     looks
    0.38
    rette
    0.38
     offline
    0.37
    innt
    0.37
     thermonuclear
    0.36
    Activations Density 0.010%

    No Known Activations