© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6702
    Prev
    Next
    INDEX
    Explanations

    the word "example"

    oai_token-act-pair · gemini-2.0-flash

    example

    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
    Portale
    -0.78
     d
    -0.77
     dr
    -0.67
    jsdelivr
    -0.66
     ch
    -0.65
    ftrag
    -0.65
    claimer
    -0.64
     l
    -0.64
    vaadin
    -0.62
     Cand
    -0.62
    POSITIVE LOGITS
     Monfieur
    1.52
     quæ
    1.26
     Efq
    1.25
     houſe
    1.23
     ſche
    1.22
     Jefus
    1.20
     Majefty
    1.19
     myſelf
    1.14
     auffi
    1.13
     pleaſure
    1.13
    Activations Density 1.186%

    No Known Activations