© 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. 229172
    Prev
    Next
    INDEX
    Explanations

    方式 (methods/ways)

    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
    н
    0.96
    ও
    0.92
    вае
    0.89
    ى
    0.89
    i
    0.86
    بالإنجليزية
    0.85
    am
    0.84
    在
    0.84
    يد
    0.84
     conflic
    0.84
    POSITIVE LOGITS
    s
    1.61
    {
    1.25
    ים
    1.15
    -
    1.14
    dan
    1.06
    ের
    0.99
    \
    0.96
     was
    0.93
    ת
    0.93
    ታ
    0.93
    Activations Density 0.000%

    No Known Activations