© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3769
    Prev
    Next
    INDEX
    Explanations

    text after a series of dashes, indicating the start of a new comment

    oai_token-act-pair · gemini-2.0-flash

    Online discussions/comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     AssemblyCulture
    -0.47
     "));
    -0.46
     qu
    -0.42
    tagHelperRunner
    -0.41
     sockaddr
    -0.40
    banez
    -0.40
    fährt
    -0.40
    monton
    -0.39
    itisation
    -0.38
    BCA
    -0.38
    POSITIVE LOGITS
    Obrázky
    0.92
    XmlAccessType
    0.83
    Vidite
    0.77
     oprot
    0.75
     ejus
    0.71
    Espèce
    0.71
     jspb
    0.69
     lenker
    0.68
     تانيه
    0.67
    adaran
    0.67
    Activations Density 8.924%

    No Known Activations