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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12558
    Prev
    Next
    INDEX
    Explanations

    code-related terms, especially those related to selection and current states

    oai_token-act-pair · gemini-2.0-flash

    current

    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
     myſelf
    -0.87
     ſeveral
    -0.76
     houſe
    -0.76
     المعيارى
    -0.75
     themſelves
    -0.75
     itſelf
    -0.73
     himſelf
    -0.73
     Infórmanos
    -0.72
    ſelves
    -0.71
     Efq
    -0.71
    POSITIVE LOGITS
    providedIn
    0.52
     ne
    0.49
     sa
    0.47
     memb
    0.44
    ‌شده
    0.43
    得到
    0.43
    negan
    0.42
     tiêu
    0.42
     lo
    0.42
    ngu
    0.42
    Activations Density 1.809%

    No Known Activations