© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211937
    Prev
    Next
    INDEX
    Explanations

    live animals and birds

    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_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sempat
    0.49
     తిరిగి
    0.45
     dilengkapi
    0.45
     desgr
    0.44
     է
    0.44
     foram
    0.42
    ′
    0.42
     श्रीम
    0.42
    ୫
    0.42
     logam
    0.42
    POSITIVE LOGITS
     spontaneous
    0.46
    цу
    0.45
     spontaneously
    0.45
    ூர்
    0.40
    able
    0.40
    abase
    0.38
    sample
    0.38
     spont
    0.38
    জের
    0.38
    Sample
    0.38
    Activations Density 0.000%

    No Known Activations