© 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. 4278
    Prev
    Next
    INDEX
    Explanations

    language related to American sports, especially football and basketball

    oai_token-act-pair · gemini-2.0-flash

    verbs associated with completion or result

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

    completion

    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
    KommentareTeilen
    -0.81
    
    -0.71
    wiſe
    -0.68
     }}"></
    -0.67
     leſs
    -0.65
    AnimationsModule
    -0.64
     themſelves
    -0.64
    AccessorTable
    -0.64
    Personendaten
    -0.64
    extAlignment
    -0.63
    POSITIVE LOGITS
     has
    0.63
     finished
    0.59
     finishes
    0.57
     is
    0.56
     finish
    0.51
     finishing
    0.49
     leads
    0.47
     Finished
    0.45
     contains
    0.45
     will
    0.43
    Activations Density 0.907%

    No Known Activations