© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134266
    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_6_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
    ду
    0.94
    ،
    0.84
    )}
    0.81
    ين
    0.79
    а
    0.79
    п
    0.79
    𝕤
    0.78
    ς
    0.78
    ্প
    0.77
     в
    0.75
    POSITIVE LOGITS
    in
    0.92
    ab
    0.89
    ä
    0.89
    1
    0.86
    ición
    0.85
    inę
    0.85
     後
    0.81
    fält
    0.80
    om
    0.79
    områ
    0.76
    Activations Density 0.000%

    No Known Activations