© 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. 167240
    Prev
    Next
    INDEX
    Explanations

    2

    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
     judge
    0.62
     Judge
    0.61
     court
    0.57
     courts
    0.56
    Judge
    0.55
    judge
    0.53
    判
    0.52
     суд
    0.51
     courtroom
    0.50
     судеб
    0.50
    POSITIVE LOGITS
     mercato
    0.37
    앉
    0.37
     Neurosci
    0.35
    締め
    0.35
     空気
    0.34
     backstage
    0.34
     vrchol
    0.34
    〆
    0.34
     smokers
    0.34
     Interviews
    0.34
    Activations Density 0.005%

    No Known Activations