© 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. 13873
    Prev
    Next
    INDEX
    Explanations

    information related to legal citations, academic papers and regulatory code

    oai_token-act-pair · gemini-2.0-flash

    Spelled-out 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
    ULUM
    -0.68
    InteropServices
    -0.67
    ientôt
    -0.62
    
    -0.61
    المشاركات
    -0.61
    一見
    -0.61
    labus
    -0.59
     étoit
    -0.59
     connues
    -0.59
    ssysteme
    -0.59
    POSITIVE LOGITS
    tagHelperRunner
    0.81
     ten
    0.70
    SequentialGroup
    0.66
    ConstraintMaker
    0.63
     Fifteen
    0.63
    Fifteen
    0.63
     eleven
    0.61
     fifteen
    0.60
    StoreMessageInfo
    0.60
     five
    0.59
    Activations Density 15.920%

    No Known Activations