© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7158
    Prev
    Next
    INDEX
    Explanations

    words that appear to connect different parts of speech

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    WithIdentifier
    -0.47
    herself
    -0.44
     lui
    -0.43
    ENTLY
    -0.40
     Betracht
    -0.40
    agoza
    -0.40
     leksikon
    -0.39
    yourself
    -0.38
    seitig
    -0.38
    ErrMsg
    -0.38
    POSITIVE LOGITS
     his
    1.17
     my
    1.08
     svého
    0.92
     свою
    0.89
     seu
    0.89
     savo
    0.88
     своих
    0.88
     their
    0.88
     своего
    0.88
     своем
    0.87
    Activations Density 6.117%

    No Known Activations