© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136901
    Prev
    Next
    INDEX
    Explanations

    SPICE circuit simulation

    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_37_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
     }{}_{\
    0.43
     nettement
    0.42
    ាយ
    0.41
    autocon
    0.41
     perception
    0.39
     percepción
    0.39
     interventi
    0.38
     "'";
    0.38
     kuda
    0.38
     Perception
    0.37
    POSITIVE LOGITS
     Asia
    0.39
    modelo
    0.38
     एशिया
    0.38
    доби
    0.37
    Mismatch
    0.37
     polarized
    0.36
     KP
    0.36
     ASU
    0.34
    Missouri
    0.34
    🌱
    0.34
    Activations Density 0.003%

    No Known Activations