© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54023
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_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
    h
    0.52
     hy
    0.44
    dx
    0.44
     Emer
    0.43
     दरम्यान
    0.43
     und
    0.43
    iz
    0.42
     übernommen
    0.42
    cx
    0.41
     indépend
    0.41
    POSITIVE LOGITS
     tuples
    0.51
     እንቅ
    0.51
     satisfies
    0.47
    uenti
    0.47
    Have
    0.46
    Hum
    0.46
    ্রাজ
    0.45
    흄
    0.45
    пами
    0.44
    Will
    0.43
    Activations Density 0.000%

    No Known Activations