© 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-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11668
    Prev
    Next
    INDEX
    Explanations

    words that contain the letters "h" and "ur" or "ph," or words that commonly have those letters in them

    oai_token-act-pair · gemini-2.0-flash

    wh/Sh

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    able
    -1.42
    ability
    -1.08
    age
    -0.98
    a
    -0.98
    ade
    -0.97
    ah
    -0.96
    ages
    -0.94
    ain
    -0.94
    ach
    -0.93
    am
    -0.92
    POSITIVE LOGITS
    Hentet
    0.52
    น
    0.43
    salon
    0.41
     Asser
    0.41
     кӀ
    0.41
    inston
    0.41
    sic
    0.40
    PRNewswire
    0.39
    s
    0.39
    sa
    0.38
    Activations Density 4.846%

    No Known Activations