© 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. 11506
    Prev
    Next
    INDEX
    Explanations

    words related to parents and childhood

    oai_token-act-pair · gemini-2.0-flash

    parental

    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
     parents
    -2.56
     parent
    -2.47
     Parents
    -2.45
     father
    -2.39
     Parent
    -2.33
    Parents
    -2.31
    Parent
    -2.28
    parent
    -2.28
    parents
    -2.25
     parental
    -2.23
    POSITIVE LOGITS
     שוליים
    0.48
    eser
    0.45
     dentelle
    0.44
     متعلقه
    0.43
    mani
    0.41
    Anatomy
    0.41
    }],
    0.41
    nton
    0.39
    ів
    0.39
     fig
    0.39
    Activations Density 2.593%

    No Known Activations