© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132206
    Prev
    Next
    INDEX
    Explanations

    deals with disclaimer

    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_6_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
    v
    1.52
    م
    1.48
    w
    1.41
    h
    1.27
    ви
    1.23
    b
    1.21
    z
    1.21
    p
    1.16
    м
    1.16
    for
    1.04
    POSITIVE LOGITS
    ↵
    1.22
    ↵↵
    1.11
     beaded
    0.86
     as
    0.81
    ža
    0.80
     دیں
    0.80
    ša
    0.79
     reprim
    0.79
     marketed
    0.78
     profiling
    0.76
    Activations Density 0.001%

    No Known Activations