© 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. 15854
    Prev
    Next
    INDEX
    Explanations

    code with numbers, or numbers in general

    oai_token-act-pair · gemini-2.0-flash

    64-bit systems and numbers

    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
    setVerticalGroup
    -0.71
    djangoproject
    -0.61
     مشين
    -0.60
     twenty
    -0.60
    clable
    -0.57
    UserScript
    -0.57
     réessayer
    -0.57
    UIControlState
    -0.56
    "]]
    -0.55
    XmlAccessType
    -0.55
    POSITIVE LOGITS
    TypedDataSet
    0.57
     تانيه
    0.52
     Learner
    0.48
    ArgsConstructor
    0.48
    stdc
    0.48
    roffenen
    0.48
    MLLoader
    0.44
     Vallée
    0.44
     lumineuse
    0.43
     opérateur
    0.43
    Activations Density 1.066%

    No Known Activations