© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15751
    Prev
    Next
    INDEX
    Explanations

    the word "confident"

    oai_token-act-pair · gemini-2.0-flash

    confident

    np_max-act · gemini-2.0-flash

    confident

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     věci
    -0.70
     hjel
    -0.70
     purpoſe
    -0.68
     tiegħek
    -0.68
     complètes
    -0.67
     preghiera
    -0.65
     noastre
    -0.65
     enfans
    -0.64
     isolato
    -0.64
     död
    -0.63
    POSITIVE LOGITS
     AssemblyTitle
    0.95
     BoxFit
    0.90
    antMatchers
    0.82
     pageContext
    0.82
    zzleHttp
    0.81
     INTERESAR
    0.80
    numerusform
    0.79
    AddTagHelper
    0.79
     MainAxisSize
    0.78
    usercontent
    0.77
    Activations Density 0.899%

    No Known Activations