© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7207
    Prev
    Next
    INDEX
    Explanations

    a variety of text features including formatting, non-English text, numbers, letters, and special characters

    oai_token-act-pair · gemini-2.0-flash

    Code, unicode, math

    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
    ，
    -0.49
    心
    -0.48
     Ptole
    -0.48
    下
    -0.47
    。
    -0.44
    />";
    -0.44
    得
    -0.44
    落
    -0.43
    片
    -0.43
    的
    -0.42
    POSITIVE LOGITS
     kasarigan
    0.46
     nakalista
    0.44
     تضيفلها
    0.43
     defaultstate
    0.42
    एँ
    0.42
     विश्वसनीयता
    0.40
    OGND
    0.40
    :✨
    0.40
    存于互联网档案馆
    0.39
    posedge
    0.39
    Activations Density 0.112%

    No Known Activations