© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 11234
    Prev
    Next
    INDEX
    Explanations

    to-infinitives often appearing in scientific and technical writings

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    providedIn
    -0.60
    }))
    
    -0.60
    })->
    -0.59
     flushing
    -0.59
     AssemblyProduct
    -0.58
    multer
    -0.56
    copying
    -0.55
     copying
    -0.54
     nargin
    -0.54
     looping
    -0.53
    POSITIVE LOGITS
     recruit
    0.75
     climb
    0.71
     edit
    0.69
     build
    0.67
     extract
    0.65
     cook
    0.65
     convert
    0.65
     hire
    0.64
    ecycle
    0.63
     manage
    0.63
    Activations Density 2.259%

    No Known Activations