© 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. 132520
    Prev
    Next
    INDEX
    Explanations

    gray white

    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
    life
    0.52
     जीवन
    0.52
    LIFE
    0.48
    -
    0.47
    ‐
    0.47
    Life
    0.45
     life
    0.44
     života
    0.44
    ־
    0.44
    world
    0.43
    POSITIVE LOGITS
     Belmont
    0.40
     Limb
    0.38
    istles
    0.38
    íss
    0.38
    atiu
    0.38
     भरी
    0.37
    𝙷
    0.37
     bellow
    0.37
     Bél
    0.36
     भरे
    0.36
    Activations Density 0.004%

    No Known Activations