© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9604
    Prev
    Next
    INDEX
    Explanations

    code snippets and XML/HTML tags

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     mu
    -0.51
     da
    -0.46
     c
    -0.45
     F
    -0.44
     di
    -0.43
     định
    -0.43
     es
    -0.43
     gri
    -0.42
    hen
    -0.42
     con
    -0.42
    POSITIVE LOGITS
     مشين
    1.22
    Personendaten
    1.20
    InjectAttribute
    1.16
     &___
    1.07
     resourceCulture
    1.06
    contentLoaded
    1.04
     ModelExpression
    1.02
     betweenstory
    1.02
    SequentialGroup
    1.02
    MLLoader
    1.02
    Activations Density 0.655%

    No Known Activations