© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 80489
    Prev
    Next
    INDEX
    Explanations

    year old

    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_29_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
    擅
    0.38
     знают
    0.34
     ہُ
    0.33
    冷蔵
    0.33
     знали
    0.33
     знает
    0.33
     conocen
    0.32
     знал
    0.32
     beruf
    0.32
     entrepreneurial
    0.31
    POSITIVE LOGITS
     astronaut
    0.42
     asigur
    0.40
     कट
    0.40
     Treaty
    0.40
     changements
    0.38
     தேர்த
    0.37
    astronaut
    0.36
    獠
    0.36
    నుంది
    0.36
     komfort
    0.36
    Activations Density 0.005%

    No Known Activations