© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 498
    Prev
    Next
    INDEX
    Explanations

    sentences that introduce an explanation or justification

    oai_token-act-pair · gemini-2.0-flash

    Building upon something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    contentLoaded
    -0.59
     impactos
    -0.58
    خته
    -0.53
     ivelany
    -0.52
     gái
    -0.52
     aikaa
    -0.51
     supplémentaires
    -0.51
     Pronto
    -0.51
     ujedno
    -0.51
    Specifier
    -0.50
    POSITIVE LOGITS
    createCanvas
    0.68
     الحره
    0.66
     relies
    0.58
     relying
    0.57
    --)
    0.55
    rijfs
    0.54
     rely
    0.54
    ())))
    0.52
    featureID
    0.51
     getBase
    0.50
    Activations Density 1.346%

    No Known Activations