© 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. 12296
    Prev
    Next
    INDEX
    Explanations

    code or code-like text that includes the word "pan"

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    webElementXpaths
    -0.83
    RenderAtEndOf
    -0.76
    Autoritní
    -0.69
    ItemGroup
    -0.68
    featureID
    -0.68
    yntaxException
    -0.67
    ListItemIcon
    -0.66
    Geplaatst
    -0.64
     disambiguazione
    -0.64
    OGND
    -0.59
    POSITIVE LOGITS
    abestanden
    0.49
    ]){
    0.44
     Taktlose
    0.41
    ніципа
    0.40
     randint
    0.39
    ///</
    0.38
    Simple
    0.37
    Self
    0.37
    VIAF
    0.37
     Qu
    0.36
    Activations Density 7.352%

    No Known Activations