© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201521
    Prev
    Next
    INDEX
    Explanations

    forward slash

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     bird
    0.47
     wildlife
    0.46
    鸟
    0.45
     Bird
    0.43
    Bird
    0.42
    bird
    0.42
     tons
    0.42
    璫
    0.40
     educate
    0.40
    心思
    0.40
    POSITIVE LOGITS
     Graphics
    0.44
     Fif
    0.44
    panic
    0.38
     Mol
    0.38
     графи
    0.37
    阜
    0.37
     graphics
    0.36
    🙏
    0.36
     ब्रे
    0.36
     ग्राफ
    0.35
    Activations Density 0.000%

    No Known Activations