© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98943
    Prev
    Next
    INDEX
    Explanations

    Lex Fridman podcast and world history

    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_14_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
    ä
    0.61
    rends
    0.54
    ò
    0.53
    ünden
    0.51
    robes
    0.50
     gär
    0.50
    ì
    0.50
     à
    0.50
    ashions
    0.50
    rän
    0.49
    POSITIVE LOGITS
    ྞ
    0.57
     vasculaire
    0.54
    ྜ
    0.53
     oscillator
    0.52
     innervation
    0.51
     intracellular
    0.49
     ৭৭
    0.49
     intravascular
    0.48
     postoperative
    0.48
    IZA
    0.47
    Activations Density 0.003%

    No Known Activations