© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11675
    Prev
    Next
    INDEX
    Explanations

    code snippets, likely from a variety of programming languages

    oai_token-act-pair · gemini-2.0-flash

    code punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     brackish
    -0.62
     rosin
    -0.59
     PRT
    -0.58
     apothe
    -0.58
     barbarian
    -0.57
    theless
    -0.57
     RTA
    -0.57
     afield
    -0.56
     creeper
    -0.56
     sorcer
    -0.55
    POSITIVE LOGITS
    OGND
    0.57
     â
    0.56
    ...@
    0.56
    *>(
    0.53
    `)
    0.53
     Einwilligung
    0.53
    )\\
    0.53
     […]
    0.52
    )}{
    0.52
    /}{
    0.52
    Activations Density 13.321%

    No Known Activations