© 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. 2238
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     Kwiatkowski
    0.34
    疇
    0.32
    newer
    0.31
     Msg
    0.31
    ικοί
    0.31
     Soci
    0.31
     Alloc
    0.31
    hover
    0.30
    ளது
    0.30
    VSLU
    0.30
    POSITIVE LOGITS
    䐂
    0.40
     नाइन
    0.38
     tubes
    0.37
     COLUMN
    0.37
    房子
    0.37
     ग्रामीणों
    0.37
     carry
    0.36
     villages
    0.36
     helpers
    0.36
    村民
    0.36
    Activations Density 0.060%

    No Known Activations