© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202787
    Prev
    Next
    INDEX
    Explanations

    Ford

    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
    ING
    1.17
    <unused416>
    1.08
    <unused584>
    0.98
    แรม
    0.98
    <0x0D>
    0.98
     oligonucle
    0.97
     erythrocytes
    0.97
    <unused580>
    0.96
    де
    0.96
    <unused1919>
    0.96
    POSITIVE LOGITS
    ka
    0.86
    isch
    0.83
    seits
    0.82
    ilir
    0.80
    ía
    0.78
    sh
    0.76
    ción
    0.76
    c
    0.75
    τή
    0.74
     is
    0.72
    Activations Density 0.000%

    No Known Activations