© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155226
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Khal
    0.43
     voy
    0.42
     lup
    0.42
    管
    0.41
     Lung
    0.41
    Richard
    0.40
     lined
    0.40
    Samb
    0.40
     Khal
    0.39
     Samir
    0.39
    POSITIVE LOGITS
    Joel
    0.52
     Joel
    0.50
    Josh
    0.47
     Josh
    0.43
     Hj
    0.42
    patrick
    0.39
    Julia
    0.39
    hj
    0.39
    <0xEC>
    0.38
    Jos
    0.38
    Activations Density 0.001%

    No Known Activations