© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249281
    Prev
    Next
    INDEX
    Explanations

    sections/parts

    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_56_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
     parts
    0.54
     Parts
    0.42
     respet
    0.41
    Parts
    0.41
     "
    0.38
     bagian
    0.38
    ising
    0.37
     parte
    0.37
     уго
    0.37
     حصے
    0.37
    POSITIVE LOGITS
     कस
    0.38
    磬
    0.37
     വിശ
    0.36
    〠
    0.36
     göster
    0.36
     Guadalupe
    0.36
     معرفی
    0.35
    介紹
    0.35
     காட்ட
    0.35
    ීය
    0.35
    Activations Density 0.000%

    No Known Activations