© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4530
    Prev
    Next
    INDEX
    Explanations

    the fragment 'fac', often found at the beginning of words associated with facilitation or factual data

    oai_token-act-pair · gemini-2.0-flash

    Fac

    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
    AnchorStyles
    -0.68
    PRWEB
    -0.63
    findpost
    -0.61
    PRNewswire
    -0.58
    readystatechange
    -0.58
    ########.
    -0.56
    styleUrls
    -0.56
     onCreateView
    -0.54
    Newswire
    -0.54
    
    -0.53
    POSITIVE LOGITS
     superpowers
    0.50
    ulto
    0.48
    bootstrapcdn
    0.47
    cules
    0.46
     Strepto
    0.45
    TableBody
    0.45
     SIB
    0.45
     Deut
    0.45
    ulite
    0.44
    uscular
    0.44
    Activations Density 0.585%

    No Known Activations