© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6750
    Prev
    Next
    INDEX
    Explanations

    code snippets or configuration segments

    oai_token-act-pair · gemini-2.0-flash

    Code related to forms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     صوتيه
    -0.52
    Personendaten
    -0.50
    UrlResolution
    -0.47
     Disqus
    -0.46
     anz
    -0.45
    newswire
    -0.45
     ['$
    -0.44
     Oficial
    -0.44
     Chopper
    -0.44
    adf
    -0.44
    POSITIVE LOGITS
     Form
    0.70
    OGND
    0.67
    enderror
    0.66
     BorderRadius
    0.65
    Form
    0.60
     formulaire
    0.59
    ________________
    0.57
    +#+#
    0.55
     LoginForm
    0.54
    ofd
    0.54
    Activations Density 1.421%

    No Known Activations