© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9666
    Prev
    Next
    INDEX
    Explanations

    uses filler words and punctuation when discussing software libraries and other programming elements

    oai_token-act-pair · gemini-2.0-flash

    Code and functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     DELETE
    -0.74
     SHARE
    -0.73
     WRITE
    -0.72
     незавершена
    -0.72
     DRIVE
    -0.71
    WATCH
    -0.71
    share
    -0.71
    SHARE
    -0.71
     peindre
    -0.70
     Wins
    -0.69
    POSITIVE LOGITS
    fortawesome
    0.45
    ValueStyle
    0.41
    libft
    0.39
    **/
    0.38
    protoimpl
    0.37
    #+#
    0.37
    Демографія
    0.35
    "]();
    0.35
    УП
    0.34
    hu
    0.33
    Activations Density 1.891%

    No Known Activations