© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196765
    Prev
    Next
    INDEX
    Explanations

    optimizer.step()

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     cốc
    0.39
    qq
    0.38
     chưa
    0.37
     grabando
    0.37
    लामा
    0.36
     fazendo
    0.36
    뭐
    0.35
    ٔ
    0.35
    izando
    0.35
     cua
    0.35
    POSITIVE LOGITS
     Thermo
    0.41
     Premium
    0.39
     Lebensmittel
    0.39
     Anywhere
    0.39
     PREMIUM
    0.38
     Biotech
    0.38
     Geos
    0.38
     Dro
    0.36
     Geom
    0.36
     ambientales
    0.36
    Activations Density 0.000%

    No Known Activations