© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9316
    Prev
    Next
    INDEX
    Explanations

    dates, numbers and origins or beginnings

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'birth'

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

    birth

    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
    -0.84
     Bourgoin
    -0.71
     चीज़ों
    -0.69
     purpoſe
    -0.61
     mergeFrom
    -0.60
    adaptiveStyles
    -0.60
     {}));
    -0.59
    HtmlAttribute
    -0.59
     themſelves
    -0.59
    })->
    -0.59
    POSITIVE LOGITS
     birth
    2.47
     born
    2.20
     Birth
    1.98
    birth
    1.90
     Born
    1.88
    Birth
    1.84
     BIRTH
    1.81
    Born
    1.73
    born
    1.73
     BORN
    1.70
    Activations Density 1.795%

    No Known Activations