© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5768
    Prev
    Next
    INDEX
    Explanations

    the start of words starting with "exp"

    oai_token-act-pair · gemini-2.0-flash

    exp

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Normdatei
    -0.61
    ="@+
    -0.56
    ConverterFactory
    -0.55
    providedIn
    -0.52
    BeginInit
    -0.52
    sizeCache
    -0.52
    oyi
    -0.52
    Groetjes
    -0.51
    期刊论文
    -0.51
    apé
    -0.50
    POSITIVE LOGITS
     fallu
    0.52
    
    0.52
    Viitteet
    0.51
     modifié
    0.48
    ectoria
    0.47
    følgelig
    0.47
     réguli
    0.47
     Penalties
    0.47
     vectorielles
    0.45
     محفوظة
    0.45
    Activations Density 0.714%

    No Known Activations