© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38677
    Prev
    Next
    INDEX
    Explanations

    shapes and names

    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_11_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
     jednog
    0.57
     dát
    0.52
    嬙
    0.51
     jednego
    0.49
     положении
    0.49
    其他
    0.46
     فى
    0.46
    hubungan
    0.46
    urized
    0.46
    менование
    0.46
    POSITIVE LOGITS
    bery
    0.59
    fasta
    0.56
    anta
    0.56
    ota
    0.55
    z
    0.55
    ody
    0.54
    EN
    0.54
    gan
    0.54
    oti
    0.53
     b
    0.52
    Activations Density 0.008%

    No Known Activations