© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11325
    Prev
    Next
    INDEX
    Explanations

    words related to summaries and general ideas

    oai_token-act-pair · gemini-2.0-flash

    overall understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Straße
    -0.56
    quar
    -0.48
    loh
    -0.48
    aspetto
    -0.47
     Technical
    -0.47
     technical
    -0.45
    jano
    -0.45
    ceğim
    -0.45
    ibt
    -0.44
    Technical
    -0.44
    POSITIVE LOGITS
    :✨
    1.05
    MessageTagHelper
    0.81
    UnsafeEnabled
    0.79
    #+#
    0.79
    afficheront
    0.76
    mybatisplus
    0.71
    protoimpl
    0.67
    Rüyada
    0.65
    Abitanti
    0.64
     Wikimedijinoj
    0.63
    Activations Density 1.303%

    No Known Activations