© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104792
    Prev
    Next
    INDEX
    Explanations

    =

    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_44_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
    点
    0.39
    obot
    0.37
    bord
    0.37
     dripping
    0.36
    िब
    0.36
    鍚
    0.35
    nob
    0.35
    mane
    0.35
    othed
    0.35
    ими
    0.35
    POSITIVE LOGITS
     reaksi
    0.39
     foliis
    0.38
    hepatic
    0.38
     citer
    0.38
     physic
    0.38
     localised
    0.37
    cyclo
    0.37
     chose
    0.37
     luna
    0.37
    $...
    0.37
    Activations Density 0.000%

    No Known Activations