© 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. 111588
    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
    u
    2.03
    ing
    1.57
    ad
    1.55
    I
    1.44
    il
    1.43
    es
    1.42
    w
    1.41
    ap
    1.23
    at
    1.20
    as
    1.16
    POSITIVE LOGITS
     dolayı
    1.05
     to
    0.92
     razum
    0.89
    ്രീ
    0.88
     نہیں۔
    0.88
    commonByteArray
    0.86
     on
    0.85
     Ә
    0.85
     Что
    0.84
     চুরি
    0.84
    Activations Density 0.000%

    No Known Activations