© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205806
    Prev
    Next
    INDEX
    Explanations

    blocking

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    istiche
    0.43
     umożliw
    0.41
     reforming
    0.41
     memungkinkan
    0.41
    愔
    0.41
     ermöglichen
    0.40
     enables
    0.40
     diversifying
    0.40
     allowing
    0.39
     occurring
    0.39
    POSITIVE LOGITS
    block
    0.37
    (/^
    0.37
    сками
    0.37
    gav
    0.36
     Py
    0.36
    гами
    0.36
     Tennessee
    0.35
    vind
    0.35
     mats
    0.35
    Tarefa
    0.35
    Activations Density 0.003%

    No Known Activations