© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11806
    Prev
    Next
    INDEX
    Explanations

    descriptions of houses and their features

    oai_token-act-pair · gemini-2.0-flash

    terms associated with real estate and property features

    np_token-act-pair-logits · gpt-4o-mini

    Describes rooms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Efq
    -0.69
     Jefus
    -0.66
     Beſ
    -0.66
     ſever
    -0.63
     Reſ
    -0.62
     itſelf
    -0.60
     fubject
    -0.59
     Monfieur
    -0.59
     disambiguazione
    -0.58
     Conſ
    -0.58
    POSITIVE LOGITS
    MeasureSpec
    0.57
     Wicidata
    0.53
    WindowConstants
    0.50
     cand
    0.46
     kiệm
    0.45
    quester
    0.44
    abang
    0.44
    TemporalType
    0.44
     tür
    0.43
    ainville
    0.43
    Activations Density 0.818%

    No Known Activations