© 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. 79750
    Prev
    Next
    INDEX
    Explanations

    food dishes

    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
    schr
    0.44
     forget
    0.41
     পরমাণ
    0.40
     concentrated
    0.39
     segregated
    0.39
    benhav
    0.38
    毛
    0.38
     kè
    0.37
     tw
    0.36
     Categor
    0.36
    POSITIVE LOGITS
     N
    0.55
    𝐍
    0.46
    N
    0.44
     Н
    0.43
     г
    0.43
    David
    0.42
    Rek
    0.42
    𝗡
    0.42
     الن
    0.41
    Jack
    0.41
    Activations Density 0.001%

    No Known Activations