© 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. 226699
    Prev
    Next
    INDEX
    Explanations

    Llama 2

    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
    ется
    0.84
    ן
    0.78
     criado
    0.76
     obsług
    0.73
    లో
    0.70
    อยู่ใน
    0.68
    ให้กับ
    0.68
    ません
    0.67
    শিকান্ত
    0.66
     trgov
    0.66
    POSITIVE LOGITS
    p
    1.41
    la
    1.27
     in
    1.24
    t
    1.20
    ne
    1.14
    v
    1.06
    f
    1.05
    x
    1.04
    1
    1.03
    ال
    1.02
    Activations Density 0.004%

    No Known Activations