© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16620
    Prev
    Next
    INDEX
    Explanations

    -

    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_15_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
    acağız
    0.29
     گروه
    0.28
     Elektrokh
    0.26
    दिग्ध
    0.26
    <unused1068>
    0.26
     எண்ணிக்க
    0.25
     کودکان
    0.25
     گزینه
    0.25
     אנחנו
    0.25
    🆗
    0.25
    POSITIVE LOGITS
    _
    0.32
    -
    0.29
    *
    0.27
     compil
    0.24
    \_
    0.23
    <
    0.22
    Fun
    0.22
    Swe
    0.22
    '
    0.22
     funky
    0.21
    Activations Density 0.013%

    No Known Activations