© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91057
    Prev
    Next
    INDEX
    Explanations

    say "namespace"

    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_60_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
     it
    0.49
     attributed
    0.47
     made
    0.47
     eminent
    0.46
     outspoken
    0.45
     heartbreaking
    0.45
    <0xE2>
    0.44
     colour
    0.44
     optimisation
    0.44
     skilled
    0.43
    POSITIVE LOGITS
    NAMES
    0.63
    names
    0.59
    using
    0.57
     نام
    0.57
    name
    0.55
    nombre
    0.55
    名称
    0.55
    [
    0.55
    System
    0.54
    Nama
    0.53
    Activations Density 0.001%

    No Known Activations