© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107428
    Prev
    Next
    INDEX
    Explanations

    Corosync, Soros, or OROS

    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_2_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
    un
    1.30
    ם
    1.28
    em
    1.27
    ん
    1.24
    さ
    1.23
    ون
    1.21
    ור
    1.20
    iş
    1.19
    də
    1.18
    ob
    1.16
    POSITIVE LOGITS
     facades
    1.06
    ح
    1.01
     οποίο
    0.94
     of
    0.92
    heus
    0.89
    你有
    0.88
     volto
    0.86
     τρόπο
    0.86
    数据集
    0.84
    he
    0.84
    Activations Density 0.000%

    No Known Activations