© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11961
    Prev
    Next
    INDEX
    Explanations

    names of people, especially when followed by titles or sports positions, or in the context of birthdates.

    oai_token-act-pair · gemini-2.0-flash

    Mention of 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     birth
    -2.53
     Birth
    -2.22
     born
    -2.20
    Birth
    -2.16
    birth
    -2.16
     Born
    -2.03
    Born
    -2.03
     BIRTH
    -1.99
     BORN
    -1.94
    born
    -1.92
    POSITIVE LOGITS
     was
    0.75
    Was
    0.57
     Was
    0.55
    was
    0.54
    SuccessListener
    0.50
    ViewFeatures
    0.49
    oken
    0.44
     estava
    0.43
     comptes
    0.42
     abstrait
    0.42
    Activations Density 1.472%

    No Known Activations