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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14218
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with research studies and medical procedures

    oai_token-act-pair · gemini-2.0-flash

    procedure

    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
     procedure
    -1.88
     procedures
    -1.82
     Procedure
    -1.80
    Procedure
    -1.79
     Procedures
    -1.73
    procedure
    -1.70
    procedures
    -1.65
    Procedures
    -1.61
     PROCEDURE
    -1.59
     PROCEDURES
    -1.48
    POSITIVE LOGITS
     NSCoder
    0.64
    IntoConstraints
    0.63
    GEBURTS
    0.62
    __*/
    0.56
    ритори
    0.55
     GetEnumerator
    0.54
    Hauptartikel
    0.54
    findpost
    0.53
     unknownFields
    0.53
     isComment
    0.53
    Activations Density 11.218%

    No Known Activations