© 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. 6672
    Prev
    Next
    INDEX
    Explanations

    the word "relatively"

    oai_token-act-pair · gemini-2.0-flash

    relatively

    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
     AttributeSet
    -0.94
    GraphicsUnit
    -0.93
     JpaRepository
    -0.81
    setVerticalGroup
    -0.80
    ••••
    -0.75
     &___
    -0.74
    )|^{
    -0.73
    Autoritní
    -0.68
    cune
    -0.67
     quæ
    -0.67
    POSITIVE LOGITS
     ffilm
    0.60
     paramInt
    0.53
     withRouter
    0.52
    المراجع
    0.52
    +#+#
    0.50
    <s>
    0.49
     parado
    0.49
     SMEs
    0.48
     boneca
    0.48
     VLC
    0.48
    Activations Density 0.317%

    No Known Activations