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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4661
    Prev
    Next
    INDEX
    Explanations

    mentions of C/C++ style 0xNN numbers, dates, and names of error codes

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Tuesday
    -1.32
    Tuesday
    -1.30
     Tuesdays
    -1.17
     tuesday
    -1.13
     TUESDAY
    -1.13
    TUESDAY
    -1.07
     Monday
    -1.05
    tuesday
    -1.05
     Tues
    -1.05
    Monday
    -1.03
    POSITIVE LOGITS
    Atsauces
    0.54
    Билгалдахарш
    0.53
    日閲覧
    0.52
    ="@+
    0.51
    Бахар
    0.49
    tagHelperRunner
    0.49
    ToScroll
    0.46
     mer
    0.46
    Autoritní
    0.45
     Winaray
    0.44
    Activations Density 1.030%

    No Known Activations