© 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. 4991
    Prev
    Next
    INDEX
    Explanations

    a specific set of seemingly random characters, which might be part of some kind of code or identifier

    oai_token-act-pair · gemini-2.0-flash

    Code/technical language

    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
    LookAnd
    -0.65
    IPT
    -0.60
     setId
    -0.59
    IPs
    -0.58
     SCC
    -0.57
    MAI
    -0.56
    Étape
    -0.55
     SUT
    -0.55
    PCD
    -0.54
    AGA
    -0.54
    POSITIVE LOGITS
    (!__
    0.60
     gradova
    0.57
    #+#
    0.53
     Bioaccumulative
    0.52
     Walkover
    0.51
     AssemblyCompany
    0.49
    NewGuid
    0.48
     Bal
    0.48
    sidemargin
    0.47
    nthetic
    0.47
    Activations Density 2.281%

    No Known Activations