© 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. 198471
    Prev
    Next
    INDEX
    Explanations

    sequential processing

    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
    Wal
    0.37
    คัญ
    0.36
    寒
    0.36
     Mass
    0.35
     거야
    0.35
    correspond
    0.35
     Arist
    0.35
    pit
    0.35
     холод
    0.35
    тпу
    0.35
    POSITIVE LOGITS
    IDAE
    0.38
    ajes
    0.38
    HEL
    0.37
    కార
    0.36
     În
    0.36
     축
    0.36
    În
    0.35
    䡃
    0.35
     în
    0.35
     One
    0.34
    Activations Density 0.006%

    No Known Activations