© 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. 133958
    Prev
    Next
    INDEX
    Explanations

    Google Tag Manager (GTM)

    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
    ၅
    0.80
    that
    0.79
     фраг
    0.79
    ٥
    0.79
    acht
    0.77
    п
    0.77
    half
    0.77
     ειδ
    0.76
    <unused2138>
    0.76
    ७
    0.76
    POSITIVE LOGITS
    et
    1.09
    า
    1.01
    S
    1.00
    in
    0.98
     to
    0.95
    ad
    0.95
    </h2>
    0.90
     or
    0.89
    ia
    0.88
     at
    0.85
    Activations Density 0.000%

    No Known Activations