© 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. 133113
    Prev
    Next
    INDEX
    Explanations

    extension of the

    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
    트
    1.22
    し
    1.16
    aop
    0.99
    ض
    0.99
    $
    0.99
    ires
    0.96
    ড
    0.96
    ات
    0.93
    طم
    0.93
    ك
    0.92
    POSITIVE LOGITS
    y
    0.94
    ia
    0.92
    .
    0.89
     compañ
    0.86
     defender
    0.86
     ruler
    0.84
    ain
    0.81
    的时
    0.80
     usu
    0.79
     user
    0.78
    Activations Density 0.000%

    No Known Activations