© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4070
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to the structure and content of documents and events

    oai_token-act-pair · gemini-2.0-flash

    website content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     link
    -1.27
     Link
    -1.08
    Link
    -0.96
    link
    -0.95
     LINK
    -0.88
    LINK
    -0.85
     article
    -0.72
     링크
    -0.72
     hyperlink
    -0.69
    链接
    -0.66
    POSITIVE LOGITS
    Portail
    0.58
    sphase
    0.55
    Diweddarwch
    0.55
     tartalomajánló
    0.55
    SourceChecksum
    0.53
    irut
    0.53
     propOrder
    0.53
    rosserie
    0.52
    abestanden
    0.52
    setVerticalGroup
    0.52
    Activations Density 10.732%

    No Known Activations