© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167588
    Prev
    Next
    INDEX
    Explanations

    Dropped food, shell in, ball in

    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_34_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
    捡
    0.84
    撿
    0.73
     collecting
    0.71
     particles
    0.71
    拾
    0.71
     debris
    0.70
     Particles
    0.68
    颗粒
    0.66
     litter
    0.65
     pellets
    0.64
    POSITIVE LOGITS
    邁
    0.39
    FixedWidth
    0.38
    يئة
    0.37
     пам
    0.37
    imori
    0.36
     माय
    0.36
    Descriptors
    0.36
    惦
    0.35
    壓縮
    0.35
    實驗
    0.34
    Activations Density 0.034%

    No Known Activations