Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7165
    Prev
    Next
    INDEX
    Explanations

    sections of reports that analyze results, often related to a study or tests

    oai_token-act-pair · gemini-2.0-flash

    results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -1.16
     Efq
    -1.09
     Monfieur
    -1.06
     Majefty
    -1.02
     Jefus
    -0.98
     becauſe
    -0.97
     Eſ
    -0.96
     myſelf
    -0.95
    ſelf
    -0.93
     Houſe
    -0.92
    POSITIVE LOGITS
     kasarigan
    0.83
     propOrder
    0.79
    UserScript
    0.75
     Taktlose
    0.72
    ьаж
    0.71
    Migrations
    0.65
    -------------</
    0.64
    ckeys
    0.64
    ValueStyle
    0.64
     tartalomajánló
    0.63
    Activations Density 5.228%

    No Known Activations