© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16156
    Prev
    Next
    INDEX
    Explanations

    html view or layout tags, especially those with class assignments

    oai_token-act-pair · gemini-2.0-flash

    code/data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     betweenstory
    -0.82
    PreferredItem
    -0.66
    msgTypes
    -0.66
    complexContent
    -0.65
     Administrativna
    -0.64
    AutoField
    -0.63
    verwijspagina
    -0.62
    ]")]
    -0.60
    OCCURRED
    -0.59
     vulgaires
    -0.59
    POSITIVE LOGITS
    pop
    0.52
     M
    0.51
    cela
    0.50
     li
    0.47
    more
    0.46
    ady
    0.46
     x
    0.45
     kéo
    0.45
    cri
    0.45
     less
    0.44
    Activations Density 0.657%

    No Known Activations