© 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. 80034
    Prev
    Next
    INDEX
    Explanations

    ads

    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
    acr
    0.39
    <0x99>
    0.38
    bon
    0.37
     tak
    0.36
    städ
    0.35
     так
    0.35
    ेलो
    0.35
    Brandon
    0.34
    TAK
    0.34
    ništva
    0.34
    POSITIVE LOGITS
     ads
    0.50
     Ads
    0.47
     adverts
    0.45
     ad
    0.43
    自
    0.43
     Ad
    0.41
     af
    0.40
    Wo
    0.40
    ucket
    0.40
     Attic
    0.39
    Activations Density 0.000%

    No Known Activations