© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7730
    Prev
    Next
    INDEX
    Explanations

    code, including JSON, file paths, RTMP server errors, data structures, and progress bar parameters

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax and structures

    np_token-act-pair-logits · gpt-4o-mini

    special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    NUMX
    -1.22
    ^(@)
    -1.12
    rungsseite
    -1.05
     referrerpolicy
    -1.04
     MainAxisSize
    -1.03
    felves
    -0.98
    存于互联网档案馆
    -0.98
     $_"
    -0.96
     Efq
    -0.96
    ſelves
    -0.95
    POSITIVE LOGITS
    ;
    1.05
    /
    0.80
    <eos>
    0.78
    );
    0.75
    ();
    0.70
    :
    0.69
    .
    0.66
    <
    0.65
     =
    0.64
    [
    0.64
    Activations Density 15.015%

    No Known Activations