© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3338
    Prev
    Next
    INDEX
    Explanations

    mentions of media tours, releases, and events, especially those in italy and the UK in recent years

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    mergeFrom
    -0.57
    AnchorStyles
    -0.56
    thenia
    -0.54
    enumi
    -0.54
    ]++;
    -0.51
     }}}{
    -0.48
    ruce
    -0.48
     {}));
    -0.48
    cleros
    -0.47
    렀
    -0.47
    POSITIVE LOGITS
     ujednoznacz
    0.68
    ंदीखरीदारी
    0.55
     fhew
    0.52
    VersionUID
    0.52
     opérateur
    0.52
     Jackman
    0.52
     uſed
    0.52
     purpoſe
    0.51
    曖昧さ回避
    0.50
     anſ
    0.49
    Activations Density 1.334%

    No Known Activations