© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11412
    Prev
    Next
    INDEX
    Explanations

    descriptions of football plays

    oai_token-act-pair · gemini-2.0-flash

    uncommon or technical terms

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

    Football

    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
     Philist
    -0.63
    ]")]
    -0.62
     étoit
    -0.54
     doInBackground
    -0.52
    QMetaType
    -0.52
    chufe
    -0.50
    spesies
    -0.50
     seamen
    -0.49
     comprends
    -0.48
     étoient
    -0.47
    POSITIVE LOGITS
     lenker
    0.58
     transférez
    0.57
     defStyleAttr
    0.51
     point
    0.50
    Билгалдахарш
    0.50
     Roskov
    0.50
     CreateTagHelper
    0.49
    otá
    0.49
     Frame
    0.48
    εια
    0.48
    Activations Density 1.600%

    No Known Activations