© 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. 3577
    Prev
    Next
    INDEX
    Explanations

    language typical of legal documents that describe how someone was treated and arguments

    oai_token-act-pair · gemini-2.0-flash

    Handling of things

    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
     spiritually
    -0.77
     politically
    -0.73
     artis
    -0.70
     economically
    -0.69
     socially
    -0.68
     administr
    -0.66
     musically
    -0.66
     academically
    -0.63
     financially
    -0.63
    phys
    -0.63
    POSITIVE LOGITS
     vectorielles
    0.70
     sociala
    0.66
    entant
    0.66
     grecque
    0.65
     automatiques
    0.65
    RenderAtEndOf
    0.63
    SOUNDBITE
    0.63
     urbanas
    0.62
    absolute
    0.61
     '{@
    0.61
    Activations Density 6.698%

    No Known Activations