© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37207
    Prev
    Next
    INDEX
    Explanations

    model

    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_57_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
    strup
    0.38
    ʝ
    0.36
     accompagnée
    0.36
    sts
    0.36
     acompañada
    0.35
    nts
    0.34
     Gründe
    0.33
    लील
    0.33
    䋆
    0.33
     revival
    0.33
    POSITIVE LOGITS
     sun
    0.50
     ar
    0.44
    Sun
    0.43
     Sun
    0.43
     عطا
    0.42
     கொள்ள
    0.41
    Hors
    0.41
    enskap
    0.40
    Onset
    0.40
    Emer
    0.39
    Activations Density 0.004%

    No Known Activations