© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199170
    Prev
    Next
    INDEX
    Explanations

    |

    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_50_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
    抂
    0.36
    polyfill
    0.36
    っぱり
    0.36
     bào
    0.36
    \")
    0.35
    holders
    0.34
    becca
    0.34
    jno
    0.34
    ボール
    0.34
    ousedown
    0.34
    POSITIVE LOGITS
    ということは
    0.37
    私も
    0.36
    олові
    0.36
    olutions
    0.35
    琇
    0.35
     mActivity
    0.33
    มีการ
    0.33
    aurait
    0.33
    pecial
    0.32
     Teb
    0.32
    Activations Density 0.003%

    No Known Activations