© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6079
    Prev
    Next
    INDEX
    Explanations

    multi-line comments in code

    oai_token-act-pair · gemini-2.0-flash

    triple quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    """
    -1.62
    '''
    -1.30
    """
    -1.25
     """
    -1.12
    <bos>
    -1.09
     """
    -1.05
    '''
    -0.96
    ."""
    -0.87
    """)
    -0.86
    """"
    -0.84
    POSITIVE LOGITS
    ReusableCell
    0.81
    featureID
    0.77
    thenReturn
    0.72
     HttpNotFound
    0.71
     Roskov
    0.70
    Hochspringen
    0.68
    ConverterFactory
    0.67
    tvguidetime
    0.67
    URLException
    0.65
     ddelweddau
    0.65
    Activations Density 1.395%

    No Known Activations