© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132339
    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_6_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
    че
    0.86
     équ
    0.81
     for
    0.80
     neutralize
    0.79
    は
    0.79
    вая
    0.79
    Мы
    0.78
     evacuate
    0.78
    드
    0.78
     equalize
    0.76
    POSITIVE LOGITS
    ä
    1.25
    ص
    1.02
    and
    0.91
    AS
    0.88
    as
    0.87
    ina
    0.85
    SA
    0.84
    RA
    0.81
    ert
    0.81
    to
    0.80
    Activations Density 0.000%

    No Known Activations