© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83817
    Prev
    Next
    INDEX
    Explanations

    assignable to type

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     أكثر
    0.43
    كتب
    0.41
    ität
    0.41
    0.41
    達
    0.40
    зина
    0.40
    izmi
    0.39
     الطب
    0.39
    ighted
    0.39
    >
    0.39
    POSITIVE LOGITS
    वा
    0.51
     chiedere
    0.51
    ை
    0.50
    ␶
    0.49
    㓦
    0.47
    ൈ
    0.46
    ционер
    0.46
     डिस्कशन
    0.46
     হবে
    0.44
     Jeżeli
    0.44
    Activations Density 0.000%

    No Known Activations