© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7677
    Prev
    Next
    INDEX
    Explanations

    instances of the word "exact", also activating on "numerical" "graphically" and "accurate"

    oai_token-act-pair · gemini-2.0-flash

    exact

    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
     pleaſure
    -0.86
     pitié
    -0.81
     Cæsar
    -0.80
     سكانية
    -0.79
     démocr
    -0.79
     zelve
    -0.79
     anún
    -0.77
     zoude
    -0.76
     incomplète
    -0.76
     distanciation
    -0.75
    POSITIVE LOGITS
    <bos>
    0.81
     more
    0.78
     the
    0.70
     a
    0.69
     De
    0.57
     
    0.56
     Mar
    0.55
    ][:
    0.55
    IVO
    0.54
     up
    0.53
    Activations Density 1.327%

    No Known Activations