© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155620
    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_50_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
    iderm
    0.46
    Е
    0.43
    Ri
    0.42
    メ
    0.40
     gu
    0.40
     ме
    0.40
    j
    0.40
    пе
    0.40
     XM
    0.38
     mev
    0.38
    POSITIVE LOGITS
    绅
    0.40
    gents
    0.39
     अष्टमी
    0.38
    覀
    0.38
    lação
    0.38
    Barb
    0.38
     তুলনায়
    0.37
     Ага
    0.37
    hman
    0.37
     Barbados
    0.37
    Activations Density 0.000%

    No Known Activations