© 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. 228559
    Prev
    Next
    INDEX
    Explanations

    long

    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
     permanent
    0.52
    permanent
    0.52
     endure
    0.48
     perman
    0.48
     permanence
    0.46
    atir
    0.46
     forever
    0.44
    耐
    0.44
    perman
    0.43
     permanently
    0.43
    POSITIVE LOGITS
    la
    0.45
     Being
    0.44
     l
    0.44
     пан
    0.43
    Being
    0.42
     Аб
    0.42
    譚
    0.41
    ла
    0.41
     IAM
    0.41
    }`).
    0.40
    Activations Density 0.001%

    No Known Activations