© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13038
    Prev
    Next
    INDEX
    Explanations

    words related to truth, reality, or importance

    oai_token-act-pair · gemini-2.0-flash

    real

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    argli
    -0.72
    Enllaços
    -0.66
     protoimpl
    -0.62
    RTLR
    -0.59
     saites
    -0.57
     Winaray
    -0.57
     BorderRadius
    -0.57
    Посилання
    -0.56
     few
    -0.56
     INC
    -0.56
    POSITIVE LOGITS
    enumi
    0.54
     paulista
    0.52
     mergeFrom
    0.49
     Colgate
    0.47
     defences
    0.47
    illeur
    0.47
     organist
    0.46
    hieu
    0.46
    coaster
    0.46
     brasileiro
    0.45
    Activations Density 1.133%

    No Known Activations