© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89369
    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_23_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
     *$
    0.44
    გან
    0.43
    țiile
    0.42
     alrededor
    0.41
    ítő
    0.41
    owej
    0.40
    łem
    0.40
    airement
    0.40
     moisturizer
    0.39
     *
    0.39
    POSITIVE LOGITS
    気軽
    0.41
    フ
    0.40
    ライフ
    0.38
    こちらは
    0.37
     Hona
    0.37
    UNA
    0.36
    sac
    0.36
     こちら
    0.36
     tarik
    0.36
     pri
    0.35
    Activations Density 0.000%

    No Known Activations