© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131979
    Prev
    Next
    INDEX
    Explanations

    paperless, sugarless, waterless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    ha
    1.34
     as
    1.23
    _
    1.17
    ap
    1.16
    0
    1.16
    ana
    1.15
    ne
    1.11
    ied
    1.11
    9
    1.11
     are
    1.09
    POSITIVE LOGITS
    ють
    1.16
    絓
    1.05
    ید
    0.97
    UWORD
    0.95
    して
    0.91
    하여
    0.88
    䂺
    0.88
    வதற்காக
    0.87
    speople
    0.84
    в
    0.84
    Activations Density 0.001%

    No Known Activations