© 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. 15282
    Prev
    Next
    INDEX
    Explanations

    the letters "ca" followed by some other letters or numbers

    oai_token-act-pair · gemini-2.0-flash

    ca

    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
     c
    -0.66
     C
    -0.61
     مشين
    -0.55
    c
    -0.53
     
    -0.50
    Tagged
    -0.50
    ExecuteReader
    -0.50
     Don
    -0.49
     ele
    -0.48
    AYS
    -0.48
    POSITIVE LOGITS
    AsUp
    0.76
    LookAnd
    0.68
     itſelf
    0.67
    InputTagHelper
    0.65
    styleType
    0.65
    tagHelperRunner
    0.63
     MenuView
    0.63
    Personensuche
    0.62
    ConstraintMaker
    0.61
    LEncoder
    0.60
    Activations Density 0.411%

    No Known Activations