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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5225
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest related articles or content

    oai_token-act-pair · gemini-2.0-flash

    Related/linking words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SPATH
    -0.53
    Lugar
    -0.50
     Holder
    -0.50
    parsedMessage
    -0.50
     hand
    -0.48
    RegistryLite
    -0.47
     shop
    -0.47
    rit
    -0.47
     canali
    -0.47
     well
    -0.46
    POSITIVE LOGITS
     odkazy
    0.66
     Why
    0.65
    Παραπομπές
    0.62
     What
    0.62
     مشين
    0.61
     répondu
    0.61
    Personensuche
    0.59
    Why
    0.59
    Pautan
    0.58
     مرئيه
    0.57
    Activations Density 2.903%

    No Known Activations