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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12577
    Prev
    Next
    INDEX
    Explanations

    scientific language about the observation of data, what it suggests and possible contrasts

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb 'raise'

    np_token-act-pair-logits · gpt-4o-mini

    raising something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     betweenstory
    -0.65
     wikipagina
    -0.58
    GEBURTS
    -0.56
     Pingback
    -0.54
    ็จ
    -0.53
    hoek
    -0.52
     Gap
    -0.50
    ragona
    -0.50
    )_/¯
    -0.50
     parola
    -0.50
    POSITIVE LOGITS
     raises
    2.06
     raise
    2.02
     raising
    1.92
     raised
    1.77
     Raise
    1.76
     Raises
    1.70
    raise
    1.68
     Raising
    1.61
    raises
    1.57
    Raising
    1.54
    Activations Density 4.600%

    No Known Activations