© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33530
    Prev
    Next
    INDEX
    Explanations

    syntactic elements

    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_3_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
    Cs
    0.71
    C
    0.70
    ሳሪያ
    0.64
    ètes
    0.62
    bps
    0.62
     are
    0.61
    Cw
    0.61
    𝑏
    0.61
    ある
    0.61
    Lng
    0.60
    POSITIVE LOGITS
    i
    1.51
    ي
    1.26
    ið
    0.81
    ii
    0.81
    ে
    0.79
    ை
    0.77
    n
    0.75
    iu
    0.74
    iiv
    0.73
    י
    0.71
    Activations Density 0.101%

    No Known Activations