© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4472
    Prev
    Next
    INDEX
    Explanations

    snippets of Swift and Protobuf code and references to pagan and celtic origins

    oai_token-act-pair · gemini-2.0-flash

    unknownFields

    np_max-act · gemini-2.0-flash

    unknownFields

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -1.14
     itſelf
    -1.13
    "):
    -1.07
    ")));
    -1.06
    $.
    -1.00
     dieß
    -0.98
     beginnetje
    -0.98
     Jefus
    -0.98
    )";
    -0.98
    :");
    -0.95
    POSITIVE LOGITS
    <h6>
    0.84
    enumi
    0.84
    newArrayList
    0.80
    „
    0.80
    setViewName
    0.77
    Hozzáférés
    0.77
    nonatomic
    0.77
    <table>
    0.75
    enderror
    0.74
    angdong
    0.73
    Activations Density 16.686%

    No Known Activations