© 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. 61701
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ak
    1.72
    و
    1.52
    ע
    1.47
    ق
    1.33
    ك
    1.30
    ו
    1.30
    (
    1.27
    ا
    1.26
    ാ
    1.26
     be
    1.23
    POSITIVE LOGITS
    I
    1.11
    ENT
    1.05
    O
    1.02
     isang
    1.00
    OLE
    0.97
    J
    0.96
    ита
    0.96
     anggota
    0.95
    riko
    0.95
    ἱ
    0.95
    Activations Density 0.000%

    No Known Activations