© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9449
    Prev
    Next
    INDEX
    Explanations

    references to a person's relatives

    oai_token-act-pair · gemini-2.0-flash

    my

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Volatility
    -0.55
    <?
    -0.50
    thâu
    -0.50
     Mô
    -0.49
    outchouc
    -0.48
     vanske
    -0.48
    PutMapping
    -0.48
    stricken
    -0.47
    Vol
    -0.46
     tích
    -0.46
    POSITIVE LOGITS
     Grand
    0.90
     Son
    0.85
    Grand
    0.83
     Nep
    0.81
     Father
    0.76
     Mother
    0.75
    Nep
    0.75
    Son
    0.73
     Brother
    0.70
     Sister
    0.69
    Activations Density 6.767%

    No Known Activations