© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158435
    Prev
    Next
    INDEX
    Explanations

    founders and creators

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    န်း
    0.40
    adhan
    0.39
    泵
    0.39
    Pump
    0.38
     W
    0.37
     Pump
    0.37
    hya
    0.37
     darkMode
    0.36
     omission
    0.36
    pump
    0.36
    POSITIVE LOGITS
     G
    0.42
     Jessie
    0.42
     Jong
    0.42
     dav
    0.42
    Jess
    0.41
     सभाग
    0.39
     vorge
    0.38
     گ
    0.38
     Renner
    0.37
    pyridazin
    0.37
    Activations Density 0.005%

    No Known Activations