© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5649
    Prev
    Next
    INDEX
    Explanations

    contact or support information, including phone numbers, email addresses, and job titles.

    oai_token-act-pair · gemini-2.0-flash

    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_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
     avoient
    -0.98
     pouvoit
    -0.96
     feroit
    -0.94
     auroit
    -0.93
     étoit
    -0.87
     démocr
    -0.85
     fédé
    -0.85
     figliu
    -0.84
     étoient
    -0.84
     Efq
    -0.83
    POSITIVE LOGITS
     ex
    0.47
     O
    0.46
     la
    0.46
    .
    0.45
     Here
    0.44
     lo
    0.44
     {
    0.44
    LO
    0.44
     m
    0.43
     ol
    0.43
    Activations Density 8.230%

    No Known Activations