© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214504
    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_5_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
    g
    1.15
    ك
    1.15
    ка
    1.11
    до
    1.11
    M
    0.91
    𝚊
    0.91
    L
    0.88
    ך
    0.88
    j
    0.88
    ht
    0.87
    POSITIVE LOGITS
    ور
    1.19
    ল
    1.04
    লি
    0.98
    มัน
    0.96
    রূপ
    0.95
    ル
    0.91
    पी
    0.90
    রূপে
    0.90
    ल
    0.86
    ار
    0.84
    Activations Density 0.000%

    No Known Activations