© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35972
    Prev
    Next
    INDEX
    Explanations

    table borders

    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_31_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
     monasteries
    0.38
    প্প
    0.36
    തീ
    0.35
    комп
    0.35
    ТЕ
    0.35
    దయ
    0.34
     relieved
    0.34
    ))=\
    0.34
    друг
    0.34
     কার্য
    0.33
    POSITIVE LOGITS
     SUBJECT
    0.38
     xref
    0.37
    ADM
    0.36
     συ
    0.36
     idk
    0.36
    籽
    0.36
     Kd
    0.35
     φω
    0.35
    كلات
    0.35
     prothorax
    0.35
    Activations Density 0.000%

    No Known Activations