© 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. 6782
    Prev
    Next
    INDEX
    Explanations

    lines of code containing hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    Code and memory addresses

    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
    <bos>
    -3.58
     Савезне
    -1.27
     Мексичка
    -1.21
     Paglinawan
    -1.13
     itſelf
    -0.99
    '
    -0.98
     disambiguazione
    -0.97
    ’
    -0.93
     kaarangay
    -0.93
     мәкал
    -0.91
    POSITIVE LOGITS
    niv
    0.52
    inty
    0.49
    heim
    0.49
    poon
    0.48
    Ή
    0.47
    abl
    0.47
    lat
    0.47
    انه
    0.47
     manier
    0.47
    Wm
    0.47
    Activations Density 4.765%

    No Known Activations