© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7243
    Prev
    Next
    INDEX
    Explanations

    various words related to people speaking, and also words related to people in sports.

    oai_token-act-pair · gemini-2.0-flash

    code or phone calls

    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
     called
    -2.86
     Called
    -2.58
    called
    -2.50
     CALLED
    -2.41
    Called
    -2.34
     llamado
    -2.00
     llamada
    -1.98
     chamada
    -1.89
     appelé
    -1.86
     chamado
    -1.83
    POSITIVE LOGITS
     propOrder
    0.57
     deleteById
    0.50
    libft
    0.50
    RegressionTest
    0.48
    +#+#
    0.47
    фта
    0.46
    }</
    0.46
    }}}\
    0.45
    RepeatedField
    0.45
    daj
    0.44
    Activations Density 3.556%

    No Known Activations