© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 230782
    Prev
    Next
    INDEX
    Explanations

    Am + word beginning

    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
    in
    1.33
    n
    1.33
    h
    1.15
    is
    1.13
    z
    1.05
    v
    1.04
    et
    1.01
    g
    0.98
     about
    0.96
    ir
    0.96
    POSITIVE LOGITS
    τίας
    0.79
    ם
    0.78
    0
    0.75
     have
    0.72
    يا
    0.67
     siècles
    0.66
    ñas
    0.65
    眥
    0.64
    イルス
    0.63
     де
    0.61
    Activations Density 0.001%

    No Known Activations