© 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. 4238
    Prev
    Next
    INDEX
    Explanations

    times and dates

    oai_token-act-pair · gemini-2.0-flash

    Date or time stamps

    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
    AndEndTag
    -0.62
     سكانية
    -0.55
    webElementXpaths
    -0.55
    IntoConstraints
    -0.52
    "]).
    -0.52
     
    -0.50
     bul
    -0.48
     насељу
    -0.47
    )\\
    -0.45
    "]];
    -0.45
    POSITIVE LOGITS
     chré
    0.69
    5
    0.66
    3
    0.65
    8
    0.65
    4
    0.63
    مراجع
    0.63
    بوابة
    0.63
    1
    0.62
    2
    0.60
    6
    0.60
    Activations Density 16.174%

    No Known Activations