© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215117
    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_5_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
    are
    1.47
    ı
    1.39
    er
    1.38
    ied
    1.31
    an
    1.27
    ase
    1.25
    ations
    1.24
    н
    1.18
    ą
    1.18
    ant
    1.17
    POSITIVE LOGITS
    Retour
    1.38
    Viele
    1.34
    Jetzt
    1.34
    на
    1.31
    ط
    1.31
    عيد
    1.24
    Nicht
    1.24
    Otros
    1.23
    От
    1.21
    Sehr
    1.21
    Activations Density 0.000%

    No Known Activations