© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10449
    Prev
    Next
    INDEX
    Explanations

    words associated with youth or childhood

    oai_token-act-pair · gemini-2.0-flash

    children

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     girl
    -2.11
    girl
    -1.87
     Girl
    -1.81
    Girl
    -1.80
     boy
    -1.75
     GIRL
    -1.73
     girls
    -1.66
    GIRL
    -1.66
    boy
    -1.63
    girls
    -1.59
    POSITIVE LOGITS
     obstante
    0.43
    mazione
    0.40
    phorus
    0.39
    WARDS
    0.39
    στημα
    0.38
    كة
    0.37
    stwie
    0.37
    らく
    0.35
     maestra
    0.35
     aşk
    0.35
    Activations Density 1.349%

    No Known Activations