© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16035
    Prev
    Next
    INDEX
    Explanations

    mentions of family and childhood environments

    oai_token-act-pair · gemini-2.0-flash

    home

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ">//
    -0.52
     Merkel
    -0.50
    出版年
    -0.45
     geografia
    -0.45
    éal
    -0.45
     sinte
    -0.45
     mole
    -0.44
    oprote
    -0.44
     vapormax
    -0.44
    squareup
    -0.44
    POSITIVE LOGITS
     home
    1.15
    home
    0.96
    HOME
    0.92
     HOME
    0.88
    Home
    0.88
     Home
    0.81
     homes
    0.81
     hogar
    0.80
     hjemme
    0.76
    homes
    0.75
    Activations Density 4.290%

    No Known Activations