© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49911
    Prev
    Next
    INDEX
    Explanations

    first

    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_55_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
     Few
    0.42
    Few
    0.42
     few
    0.39
    ពិសេស
    0.39
     Penta
    0.38
    幾
    0.37
    ాలే
    0.37
     several
    0.37
     Guys
    0.36
    few
    0.35
    POSITIVE LOGITS
     forced
    0.44
     transplants
    0.41
     vignette
    0.41
     attuned
    0.39
     involved
    0.38
     diverted
    0.38
    펴
    0.38
     drawn
    0.37
     snatched
    0.37
     contraindicated
    0.37
    Activations Density 0.003%

    No Known Activations