© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125254
    Prev
    Next
    INDEX
    Explanations

    problematic terms

    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_37_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
    psons
    0.37
    %]
    0.37
    legenheit
    0.37
    wch
    0.36
    ]_
    0.36
     വിഷയ
    0.34
    वं
    0.34
    }&
    0.33
    IRY
    0.33
    IAA
    0.33
    POSITIVE LOGITS
     actually
    1.88
    actually
    1.73
     aslında
    1.71
     Actually
    1.69
    其实
    1.67
    其實
    1.62
    Actually
    1.59
    实际上
    1.58
     sebenarnya
    1.56
     eigenlijk
    1.52
    Activations Density 0.240%

    No Known Activations