© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11755
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to performing research

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Efq
    -0.80
     Normdatei
    -0.76
    AndroidJUnit
    -0.74
    endphp
    -0.73
     '\\;'
    -0.72
     itſelf
    -0.71
     Monfieur
    -0.69
     myſelf
    -0.69
     himſelf
    -0.68
     avoit
    -0.66
    POSITIVE LOGITS
    اظ
    0.57
    ftagPool
    0.52
     Tw
    0.47
     ta
    0.45
     hole
    0.45
    作為
    0.43
    icht
    0.42
    fia
    0.42
     Fl
    0.42
     ble
    0.42
    Activations Density 1.557%

    No Known Activations