© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6576
    Prev
    Next
    INDEX
    Explanations

    the word "emphasis" and variations, though it can be weak on the variations

    oai_token-act-pair · gemini-2.0-flash

    emphasis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    — 
    -0.71
     intent
    -0.65
     rebus
    -0.61
    ESTONE
    -0.60
    UNTAIN
    -0.60
    REEK
    -0.60
    ITHUB
    -0.60
    CURY
    -0.60
    OWSKI
    -0.59
    schaft
    -0.58
    POSITIVE LOGITS
    rungsseite
    0.89
     متعلقه
    0.89
     alugar
    0.82
     Мексичка
    0.78
     scaricare
    0.77
    picasso
    0.74
     Moslem
    0.73
     usata
    0.70
     applicazioni
    0.70
     handker
    0.69
    Activations Density 1.223%

    No Known Activations