© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209788
    Prev
    Next
    INDEX
    Explanations

    Uberman, Ubersuggest

    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_5_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
    in
    1.30
    h
    0.98
    at
    0.95
    n
    0.94
     Max
    0.88
     Ghost
    0.88
     Aquinas
    0.87
     Hogg
    0.87
     Bally
    0.86
     Carlisle
    0.86
    POSITIVE LOGITS
    '
    1.52
    ни
    1.48
    у
    1.45
    و
    1.34
    и
    1.26
    ι
    1.26
    ১
    1.20
    ע
    1.16
    که
    1.15
    ー
    1.13
    Activations Density 0.000%

    No Known Activations