© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168205
    Prev
    Next
    INDEX
    Explanations

    services

    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
     refers
    0.50
    𝟭
    0.39
     topologically
    0.38
     emerges
    0.37
    చన
    0.35
    ёз
    0.35
    ுகிறார்கள்
    0.35
    law
    0.35
    ثت
    0.34
    或者
    0.34
    POSITIVE LOGITS
    );*/
    0.41
    スの
    0.37
    ◽
    0.35
     bureau
    0.35
     mountain
    0.34
     Testing
    0.34
    minIndex
    0.34
     Hearing
    0.34
     práci
    0.34
     testing
    0.33
    Activations Density 0.001%

    No Known Activations