© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2379
    Prev
    Next
    INDEX
    Explanations

    code

    oai_token-act-pair · gemini-2.0-flash

    code and math

    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
    UrlResolution
    -0.79
    writeFieldEnd
    -0.74
     disambiguazione
    -0.74
    extAlignment
    -0.71
    complexContent
    -0.71
    principalTable
    -0.71
    ImageContext
    -0.71
    principalColumn
    -0.69
     ujednoznacz
    -0.68
     bezeichneter
    -0.68
    POSITIVE LOGITS
     ~
    2.63
    ~
    2.50
     (~
    1.84
    ~~
    1.82
    )~
    1.76
    .~
    1.72
     ~(
    1.69
    ~(
    1.65
    }~
    1.65
    (~
    1.63
    Activations Density 14.597%

    No Known Activations