© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16161
    Prev
    Next
    INDEX
    Explanations

    space shuttle launch orbit module

    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_40_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
    න
    0.41
     nonthermal
    0.38
    乱
    0.38
     clamping
    0.37
    亂
    0.37
    手机
    0.37
     物
    0.37
    સિ
    0.37
     гене
    0.36
     трубы
    0.36
    POSITIVE LOGITS
     exercise
    0.38
    exercice
    0.38
    Marco
    0.38
     ultimo
    0.38
     Pay
    0.37
     peonies
    0.37
    lių
    0.36
    Kid
    0.36
    Rv
    0.36
    Huang
    0.35
    Activations Density 0.030%

    No Known Activations