© 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. 35790
    Prev
    Next
    INDEX
    Explanations

    school and academic support

    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
    Precision
    0.41
    sizeof
    0.41
     precision
    0.40
    precision
    0.39
     ሀ
    0.38
    精度
    0.36
    берриз
    0.36
    ளோ
    0.36
     formulae
    0.35
    诓
    0.35
    POSITIVE LOGITS
     Acceleration
    0.44
     Return
    0.44
     Knoten
    0.43
     Inclusion
    0.42
     accommodate
    0.40
     acceleration
    0.40
     inclusion
    0.39
     academically
    0.38
     Disrupt
    0.38
     Kiwi
    0.38
    Activations Density 0.029%

    No Known Activations