© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 98480
    Prev
    Next
    INDEX
    Explanations

    online courses

    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_16_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
     stitched
    0.55
    aving
    0.55
     cleaned
    0.55
     kleine
    0.55
     latch
    0.55
    र
    0.54
     last
    0.54
     Dragon
    0.54
     le
    0.53
     locking
    0.53
    POSITIVE LOGITS
    앨
    0.58
    ᄏ
    0.56
     appris
    0.49
    Attrition
    0.49
     الموسم
    0.49
    싶
    0.49
     Brod
    0.48
    펩
    0.48
     regimens
    0.47
    絊
    0.47
    Activations Density 0.003%

    No Known Activations