© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80066
    Prev
    Next
    INDEX
    Explanations

    spelling errors

    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_53_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
    <0xB8>
    0.42
     Mahi
    0.40
     되었다
    0.38
     basicamente
    0.38
     básicamente
    0.38
     studia
    0.37
     ቲ
    0.36
     magnifique
    0.36
     সমাধিতে
    0.36
    жни
    0.36
    POSITIVE LOGITS
    acey
    0.42
    CANCEL
    0.39
     Connected
    0.38
    штейн
    0.38
    ereo
    0.38
    Ange
    0.38
    ursday
    0.37
    NewLabel
    0.37
    采
    0.37
    angebot
    0.37
    Activations Density 0.001%

    No Known Activations