© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14198
    Prev
    Next
    INDEX
    Explanations

    words pertaining to software features

    oai_token-act-pair · gemini-2.0-flash

    feature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     oprot
    -0.78
     AssemblyTitle
    -0.66
    JNIEnv
    -0.64
    
    -0.63
    出版年
    -0.60
    WriteAttribute
    -0.59
     chng
    -0.58
    脚注の使い方
    -0.57
    はじめに
    -0.57
    لينكات
    -0.54
    POSITIVE LOGITS
     Réponses
    0.63
     fallu
    0.50
    PageFactory
    0.50
     couverte
    0.47
    zędu
    0.46
     trésor
    0.45
     profondo
    0.43
     BoxFit
    0.43
    trades
    0.43
    őre
    0.43
    Activations Density 1.376%

    No Known Activations