© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197443
    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_27_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
    inging
    0.40
    popupIsOpen
    0.40
     pripre
    0.38
     unsuccessfully
    0.38
    ());
    0.37
     disguised
    0.36
    trying
    0.36
     Elektrokhimiya
    0.36
    ashing
    0.35
     ያለ
    0.35
    POSITIVE LOGITS
     Claw
    0.38
     Loan
    0.38
     Concepts
    0.38
    Couple
    0.37
    ATM
    0.37
     créditos
    0.37
     ஏ
    0.36
     lending
    0.35
     educa
    0.35
     sig
    0.35
    Activations Density 0.000%

    No Known Activations