© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81816
    Prev
    Next
    INDEX
    Explanations

    communism, socialism, and proletariat

    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_0_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
    -
    1.76
    ა
    1.67
    는
    1.66
    中
    1.55
    (
    1.53
    ان
    1.52
    at
    1.46
    /
    1.46
    지
    1.44
    in
    1.41
    POSITIVE LOGITS
     for
    1.59
     I
    1.45
     from
    1.22
     been
    1.13
     armored
    1.09
     一个
    1.09
     with
    1.08
     devenu
    1.07
     grueling
    1.04
     لیګ
    1.02
    Activations Density 0.000%

    No Known Activations