© 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. 5796
    Prev
    Next
    INDEX
    Explanations

    the markup symbols, references, and abbreviations used in scientific documents

    oai_token-act-pair · gemini-2.0-flash

    Technical text

    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
     TC
    -1.49
     TP
    -1.41
     TB
    -1.41
     TK
    -1.41
     TS
    -1.41
     TF
    -1.38
     TT
    -1.38
     TD
    -1.37
     TW
    -1.37
     TM
    -1.37
    POSITIVE LOGITS
    ết
    0.30
     Yên
    0.29
     nghỉ
    0.29
    prochen
    0.29
     Grote
    0.28
    SharedDtor
    0.28
     Chỉ
    0.28
     Đại
    0.27
    een
    0.27
    naeus
    0.26
    Activations Density 1.396%

    No Known Activations