© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219808
    Prev
    Next
    INDEX
    Explanations

    motorcycle bikes

    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
     अभ
    0.40
     സര്‍
    0.37
     Infections
    0.37
     Neurology
    0.35
    Travelling
    0.35
    ๏
    0.35
     mão
    0.34
     Travelling
    0.34
     ɔ
    0.34
     यात्रा
    0.33
    POSITIVE LOGITS
     indoors
    0.43
     bunting
    0.42
     crisis
    0.41
     ze
    0.40
     indoor
    0.40
     finland
    0.38
     digit
    0.37
    клар
    0.37
     p
    0.36
     outdoors
    0.36
    Activations Density 0.000%

    No Known Activations