© 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. 9847
    Prev
    Next
    INDEX
    Explanations

    under investigation or speculation

    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
    unen
    0.41
    庴
    0.39
    Примеча
    0.37
    uro
    0.36
    Примечания
    0.35
     utu
    0.34
    URO
    0.34
     വൈദ്യ
    0.33
     ઊ
    0.33
    यला
    0.33
    POSITIVE LOGITS
     speculation
    1.34
     rumors
    1.31
     rumours
    1.23
     rumor
    1.23
     speculated
    1.21
     rumores
    1.15
     rumour
    1.13
     rumoured
    1.12
     speculations
    1.09
     rumored
    1.09
    Activations Density 0.052%

    No Known Activations