© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6136
    Prev
    Next
    INDEX
    Explanations

    the word "young" followed by words describing people

    oai_token-act-pair · gemini-2.0-flash

    young

    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
     young
    -2.36
    Young
    -1.98
    young
    -1.98
     Young
    -1.92
     YOUNG
    -1.87
    YOUNG
    -1.73
     junge
    -1.73
     jungen
    -1.63
     jeune
    -1.61
     giovane
    -1.55
    POSITIVE LOGITS
    rénées
    0.48
     DBNull
    0.47
     Fuentes
    0.47
    olisme
    0.46
     BrowserModule
    0.46
    withIdentifier
    0.42
    trails
    0.42
    AuthProvider
    0.42
     propOrder
    0.41
    нель
    0.40
    Activations Density 2.092%

    No Known Activations