© 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. 4384
    Prev
    Next
    INDEX
    Explanations

    file paths and code snippets from programming languages such as PHP

    oai_token-act-pair · gemini-2.0-flash

    code paths

    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
     +
    -1.43
     $+$
    -1.23
    +
    -1.16
     $+
    -1.12
    +</
    -1.07
     +,
    -1.04
     + 
    -1.04
     +=
    -1.02
     plus
    -1.01
     $+\
    -1.01
    POSITIVE LOGITS
     .
    0.93
     .=
    0.61
    . 
    0.56
     .$
    0.56
     affichés
    0.56
     sèche
    0.54
    StreetMap
    0.54
    TabIndex
    0.54
     .(
    0.52
    . 
    0.52
    Activations Density 1.688%

    No Known Activations