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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7788
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with research studies and levels of risk.

    oai_token-act-pair · gemini-2.0-flash

    Risk and extent

    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
     balanceOf
    -0.49
    Diwedd
    -0.46
     scraped
    -0.42
     Barbuda
    -0.38
     comforter
    -0.37
    dized
    -0.37
    rifuge
    -0.36
    šina
    -0.36
    omores
    -0.36
    Aries
    -0.36
    POSITIVE LOGITS
     يتيمه
    0.72
    kháu
    0.69
    endfor
    0.62
    WebVitals
    0.60
     تضيفلها
    0.60
    /-/
    0.59
    /*
    0.59
    AxisAlignment
    0.58
     apparent
    0.58
     ?>/
    0.58
    Activations Density 14.568%

    No Known Activations