© 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. 196534
    Prev
    Next
    INDEX
    Explanations

    science

    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
     Venkates
    0.44
    諾
    0.40
    نو
    0.38
    呼
    0.38
    AppCompat
    0.37
    引っ
    0.37
    👏
    0.36
    నో
    0.36
    )}')
    0.36
    Atlantic
    0.35
    POSITIVE LOGITS
     공간
    0.43
     소재
    0.41
     오후
    0.39
     Everywhere
    0.39
     اسک
    0.39
    Observer
    0.38
     ग्रहण
    0.38
     incremento
    0.38
    스크
    0.37
     Exec
    0.37
    Activations Density 0.000%

    No Known Activations