© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63510
    Prev
    Next
    INDEX
    Explanations

    cleaning or preparing

    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_59_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
     잘
    0.43
    悪
    0.42
    esser
    0.40
    Guid
    0.38
    Oil
    0.38
    油
    0.37
    Executed
    0.37
     well
    0.36
     악
    0.36
    产生了
    0.35
    POSITIVE LOGITS
    really
    0.54
     realmente
    0.53
     really
    0.51
    Really
    0.44
    several
    0.44
     to
    0.43
     thật
    0.43
     vraiment
    0.41
     gerçekten
    0.41
     several
    0.41
    Activations Density 0.004%

    No Known Activations