© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 21878
    Prev
    Next
    INDEX
    Explanations

    open

    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_56_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
    älj
    0.34
    ataire
    0.32
     Closing
    0.32
     sath
    0.32
     แอป
    0.32
    phabet
    0.31
     kõ
    0.31
    禦
    0.31
     closing
    0.31
     morn
    0.31
    POSITIVE LOGITS
     open
    3.94
    open
    3.53
    Open
    3.05
     откры
    3.00
     Open
    2.92
    オープン
    2.89
     오픈
    2.64
     otvore
    2.63
    OPEN
    2.58
     abierto
    2.55
    Activations Density 0.211%

    No Known Activations