© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11627
    Prev
    Next
    INDEX
    Explanations

    words related to calendars, schedules, and events.

    oai_token-act-pair · gemini-2.0-flash

    meetings and events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <b>
    -0.50
    <eos>
    -0.45
    </i>
    -0.44
     prome
    -0.42
    ,
    -0.42
    :
    -0.42
     similaires
    -0.41
    @
    -0.41
    ig
    -0.41
      
    -0.41
    POSITIVE LOGITS
    ArgsConstructor
    1.00
     onCreateView
    0.97
    IsContent
    0.96
     myſelf
    0.95
    EDEFAULT
    0.94
     itſelf
    0.94
     Jefus
    0.93
     Efq
    0.93
    ſelves
    0.90
     photolibrary
    0.90
    Activations Density 33.773%

    No Known Activations