© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13750
    Prev
    Next
    INDEX
    Explanations

    short sequences of common words and names in what appear to be documents about legal or medical topics and sports

    oai_token-act-pair · gemini-2.0-flash

    Legal/code documentation

    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
     an
    -1.45
     aan
    -0.85
    An
    -0.83
    an
    -0.83
     An
    -0.76
     ivelany
    -0.71
     daran
    -0.69
    hangi
    -0.63
    endregion
    -0.61
     anz
    -0.61
    POSITIVE LOGITS
    contentLoaded
    0.53
    MessageTagHelper
    0.43
    ípios
    0.40
    TagMode
    0.39
     IFF
    0.39
    хьтан
    0.36
    IsContent
    0.36
    AutoScaleMode
    0.36
     starfish
    0.36
     isempty
    0.36
    Activations Density 0.185%

    No Known Activations