© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4466
    Prev
    Next
    INDEX
    Explanations

    ordinals and words relating to scheduled events

    oai_token-act-pair · gemini-2.0-flash

    terms related to annual events

    np_token-act-pair-logits · gpt-4o-mini

    annual

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ng
    -0.52
     NgModule
    -0.51
    specific
    -0.50
     specific
    -0.48
    JAKARTA
    -0.46
    heimer
    -0.46
     sest
    -0.44
    Specific
    -0.44
    vi
    -0.44
     Gill
    -0.44
    POSITIVE LOGITS
     annual
    1.18
    annual
    1.05
    Annual
    0.93
     Annual
    0.93
     ANNUAL
    0.87
     annuel
    0.87
    ANNUAL
    0.87
     jähr
    0.81
     annuelle
    0.79
     anuales
    0.75
    Activations Density 1.658%

    No Known Activations