© 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. 14202
    Prev
    Next
    INDEX
    Explanations

    the word "so" and other words that start with "so" followed closely by a hyphen

    oai_token-act-pair · gemini-2.0-flash

    so

    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
    ();
    -0.44
     handelt
    -0.43
    ItemBackground
    -0.41
    躇
    -0.41
    ")));
    -0.40
    DockStyle
    -0.39
    avut
    -0.38
    BagConstraints
    -0.38
    \"");
    -0.37
    Descripció
    -0.36
    POSITIVE LOGITS
    AndFlush
    0.69
     متعلقه
    0.67
    sikal
    0.63
    pportun
    0.62
    leda
    0.62
    hyo
    0.61
    jooq
    0.61
    Източници
    0.60
    tega
    0.60
    nadequate
    0.60
    Activations Density 6.651%

    No Known Activations