© 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. 13572
    Prev
    Next
    INDEX
    Explanations

    text describing engines, their performance and technical specifications

    oai_token-act-pair · gemini-2.0-flash

    engine power/torque

    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
    tagHelperRunner
    -0.78
     مشين
    -0.75
    BufferException
    -0.70
    Билгалдахарш
    -0.70
    ValueStyle
    -0.69
    ruptedException
    -0.62
     aussieht
    -0.60
    webElementXpaths
    -0.59
     HasFactory
    -0.59
     OFDb
    -0.59
    POSITIVE LOGITS
     خص
    0.49
    detta
    0.49
     вра
    0.49
    ::_('
    0.48
     figures
    0.47
    новниш
    0.46
     Dodson
    0.45
     ane
    0.44
     launched
    0.44
     outputs
    0.43
    Activations Density 1.324%

    No Known Activations