© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53142
    Prev
    Next
    INDEX
    Explanations

    if you don't

    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_30_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
     lacks
    0.41
    ないので
    0.41
    doesn
    0.38
     Doesn
    0.38
    ὴ
    0.38
     Failed
    0.36
    ่อง
    0.36
    なければ
    0.35
     cf
    0.35
    ariance
    0.35
    POSITIVE LOGITS
    Imidazole
    0.40
     कॉन्
    0.40
     सिन
    0.40
    如果你
    0.39
    гро
    0.39
    ပို
    0.38
     ايجاد
    0.38
    醪
    0.38
     получите
    0.38
    人们
    0.38
    Activations Density 0.002%

    No Known Activations