© 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. 6294
    Prev
    Next
    INDEX
    Explanations

    legal jargon related to courts and cases

    oai_token-act-pair · gemini-2.0-flash

    auditory-related terms

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

    hear

    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
    FailureListener
    -0.52
     NUKAT
    -0.51
     '\\;'
    -0.49
    Geplaatst
    -0.49
    makeText
    -0.47
    lational
    -0.46
    initializeApp
    -0.44
     Roskov
    -0.43
     /*#__
    -0.43
     vícti
    -0.42
    POSITIVE LOGITS
     hear
    0.97
     heard
    0.94
    hear
    0.90
     hears
    0.88
     hearing
    0.83
     nghe
    0.73
     listen
    0.73
     Hear
    0.71
    Hear
    0.71
     mendengar
    0.71
    Activations Density 3.865%

    No Known Activations