© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44642
    Prev
    Next
    INDEX
    Explanations

    . or ? followed by output markers

    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_22_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
    金額
    0.39
     Biel
    0.39
     فره
    0.39
     Jing
    0.38
     시장
    0.38
     видел
    0.38
     ABI
    0.37
    羢
    0.37
     आपराधिक
    0.36
     подозре
    0.36
    POSITIVE LOGITS
    ename
    0.37
    转载
    0.37
     prayers
    0.36
     uygulam
    0.36
    yml
    0.36
    plikasi
    0.36
    gment
    0.36
     surgery
    0.36
    odesmium
    0.35
    odes
    0.35
    Activations Density 0.039%

    No Known Activations