© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2113
    Prev
    Next
    INDEX
    Explanations

    code snippets, documentation, and possibly email addresses

    oai_token-act-pair · gemini-2.0-flash

    this

    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
    SourceChecksum
    -0.85
     Beattie
    -0.62
     Investigating
    -0.62
     Metcalf
    -0.61
     Investigations
    -0.59
     discoveries
    -0.59
    anskje
    -0.59
     Magee
    -0.58
    bootstrapcdn
    -0.57
     Lewin
    -0.57
    POSITIVE LOGITS
    \<^
    0.39
     alemanes
    0.38
     privados
    0.38
     regeringen
    0.35
     acier
    0.34
     gratuitas
    0.34
     jäm
    0.33
    ".
    0.32
    NUMX
    0.32
     perju
    0.31
    Activations Density 1.735%

    No Known Activations