© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9543
    Prev
    Next
    INDEX
    Explanations

    cookie flags `Secure` `HttpOnly` `path`

    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_13_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
    цвет
    0.10
     spricht
    0.09
     limón
    0.09
     beginnt
    0.09
    ных
    0.09
     bietet
    0.09
    瞑
    0.09
    mateurs
    0.09
    .”)
    0.09
    Lymph
    0.09
    POSITIVE LOGITS
    ↵↵↵
    0.10
    žu
    0.10
    '
    0.09
     oversaw
    0.09
     press
    0.09
     সময়ে
    0.09
     e
    0.08
    0.08
     n
    0.08
    ↵↵
    0.08
    Activations Density 0.039%

    No Known Activations