© 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. 11324
    Prev
    Next
    INDEX
    Explanations

    math notations

    oai_token-act-pair · gemini-2.0-flash

    exist

    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
    exitRule
    -0.74
    (!__
    -0.70
     itſelf
    -0.62
     voraus
    -0.61
    נטרנט
    -0.61
     yourselves
    -0.61
     Мексичка
    -0.60
    __(/*!
    -0.59
    prägt
    -0.59
     juſt
    -0.59
    POSITIVE LOGITS
    CGRectMake
    0.53
    +#+#
    0.51
     es
    0.50
     moments
    0.50
     times
    0.50
    DockStyle
    0.49
     period
    0.47
     CURLOPT
    0.46
     bel
    0.45
    Referencies
    0.45
    Activations Density 2.404%

    No Known Activations