© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232862
    Prev
    Next
    INDEX
    Explanations

    sound communication

    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_32_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
    Rest
    0.45
    葭
    0.40
    rest
    0.39
     resten
    0.39
    湟
    0.38
    ulie
    0.38
    luss
    0.38
    Volunteer
    0.37
    ွက်
    0.37
    ucos
    0.37
    POSITIVE LOGITS
     cans
    0.43
     kettle
    0.41
     donuts
    0.38
     fry
    0.38
     Donuts
    0.37
     Keg
    0.37
    憚
    0.37
     болез
    0.36
     seminars
    0.36
     scanners
    0.36
    Activations Density 0.002%

    No Known Activations