© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233649
    Prev
    Next
    INDEX
    Explanations

    ASCII art characters

    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
    皁
    0.40
    淥
    0.38
    ಮಾಡ
    0.36
    IMENTO
    0.36
     Shape
    0.35
    মেন
    0.35
     عرصے
    0.35
     chewed
    0.35
    䢀
    0.35
    㑼
    0.34
    POSITIVE LOGITS
    empire
    0.42
    andon
    0.40
    drive
    0.39
     Mike
    0.38
     empire
    0.38
    რობ
    0.38
    Mike
    0.37
    attribution
    0.37
    hoe
    0.37
     mike
    0.37
    Activations Density 0.000%

    No Known Activations