© 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. 9710
    Prev
    Next
    INDEX
    Explanations

    the words "deliver", "delivery", "miss", "selected", and "tasty"

    oai_token-act-pair · gemini-2.0-flash

    success or failure

    np_max-act · gemini-2.0-flash
    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
     
    -0.71
      
    -0.66
     “
    -0.65
     e
    -0.62
     of
    -0.59
    .
    -0.59
     (
    -0.58
    -
    -0.55
    ma
    -0.54
        
    -0.53
    POSITIVE LOGITS
     disambiguazione
    1.26
    InjectAttribute
    1.24
    Autoritní
    1.23
    Personendaten
    1.23
     photolibrary
    1.18
    sizeCache
    1.17
     itſelf
    1.16
     Roskov
    1.15
    EDEFAULT
    1.15
    principalColumn
    1.15
    Activations Density 0.858%

    No Known Activations