© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134963
    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_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
    reducing
    1.12
    for
    1.04
    limit
    0.86
    ין
    0.84
    limiting
    0.83
    PHIA
    0.82
    friction
    0.81
    𝓭
    0.81
    i
    0.80
    fora
    0.79
    POSITIVE LOGITS
    <0x80>
    1.00
     abhängig
    0.84
     genü
    0.81
    ī
    0.76
     entfernt
    0.75
     není
    0.74
     nared
    0.73
     niekoľ
    0.73
     weiß
    0.73
     veoma
    0.70
    Activations Density 0.000%

    No Known Activations