© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32361
    Prev
    Next
    INDEX
    Explanations

    person

    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_31_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
    zá
    0.44
     culturales
    0.40
     машин
    0.39
     uitgenodigd
    0.39
    Alleg
    0.39
    ãs
    0.38
    ガル
    0.38
    伽
    0.38
     végétaux
    0.38
    Agree
    0.38
    POSITIVE LOGITS
     throat
    0.44
     скон
    0.41
     stages
    0.41
     stitches
    0.40
     Smoothie
    0.40
     ভূমিক
    0.39
     Throat
    0.39
     throats
    0.39
     steps
    0.39
     performance
    0.39
    Activations Density 0.013%

    No Known Activations