© 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. 16283
    Prev
    Next
    INDEX
    Explanations

    capital G followed by other characters

    oai_token-act-pair · gemini-2.0-flash

    G

    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
    sizeCache
    -0.59
    OrCreate
    -0.48
    раздо
    -0.47
     P
    -0.47
     fast
    -0.47
    mouseX
    -0.45
     der
    -0.44
     val
    -0.43
    abar
    -0.43
     Q
    -0.43
    POSITIVE LOGITS
     disambiguazione
    0.80
    WriteTagHelper
    0.65
     EconPapers
    0.64
     ―――――
    0.61
    ########.
    0.60
     تانيه
    0.59
     bezeichneter
    0.58
    phosa
    0.58
     typelib
    0.58
    OGND
    0.56
    Activations Density 0.166%

    No Known Activations