© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6849
    Prev
    Next
    INDEX
    Explanations

    ail, calling, enrolled, nominated

    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_39_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
    estown
    0.41
     magnetite
    0.40
     waxing
    0.38
     album
    0.38
     gstlal
    0.38
    軋
    0.37
     precipitate
    0.37
    icios
    0.36
     piezoelectric
    0.36
    집합
    0.36
    POSITIVE LOGITS
     ail
    0.38
    签证
    0.37
    弼
    0.37
     سوری
    0.36
     الوح
    0.34
     calling
    0.34
     enrolled
    0.34
     nominated
    0.34
     дү
    0.34
    zhi
    0.34
    Activations Density 0.000%

    No Known Activations