© 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. 3775
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly those including HTML, Javascript, and JSON, and references to data handling.

    oai_token-act-pair · gemini-2.0-flash

    val

    np_max-act · gemini-2.0-flash
    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
    出版年
    -1.08
     tartalomajánló
    -1.07
     snippetHide
    -1.00
    PMailer
    -0.92
    AndEndTag
    -0.87
    tagHelperRunner
    -0.84
    GOTREF
    -0.83
    KURZBESCHREIBUNG
    -0.81
    abstractmethod
    -0.81
    MENAFN
    -0.81
    POSITIVE LOGITS
    TintMode
    0.56
     Ficha
    0.52
    DataContract
    0.51
    Distribuzione
    0.50
     öss
    0.49
    Ranked
    0.47
     Patterson
    0.46
    ->___
    0.45
    meaux
    0.45
    anstal
    0.44
    Activations Density 0.867%

    No Known Activations