© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129181
    Prev
    Next
    INDEX
    Explanations

    terraform providers

    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
    the
    1.23
    thed
    1.07
    ని
    1.03
    A
    1.03
    ን
    1.02
    આ
    0.98
    च्या
    0.96
    Ди
    0.96
    u
    0.95
    의
    0.95
    POSITIVE LOGITS
     on
    1.02
     savoir
    0.85
    ider
    0.83
     than
    0.81
    ala
    0.80
    atas
    0.79
    ase
    0.78
     says
    0.78
     buts
    0.78
    н
    0.77
    Activations Density 0.000%

    No Known Activations