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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11427
    Prev
    Next
    INDEX
    Explanations

    the verb "clear" and other verbs implying completion or payment.

    oai_token-act-pair · gemini-2.0-flash

    clear or close

    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
    (".");
    -0.73
    ]),
    -0.70
    tvguidetime
    -0.69
    $")
    -0.68
    tagHelperRunner
    -0.65
     invokingState
    -0.64
    mybatisplus
    -0.63
    >")
    -0.60
    ')}}"
    -0.60
    addCriterion
    -0.59
    POSITIVE LOGITS
     closing
    1.05
     opening
    1.02
     cleared
    0.96
     clearing
    0.95
     reopening
    0.94
     Closing
    0.93
    Opening
    0.91
    opening
    0.89
     Opening
    0.88
     opened
    0.85
    Activations Density 0.836%

    No Known Activations