© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12212
    Prev
    Next
    INDEX
    Explanations

    code related to throwing new exceptions

    oai_token-act-pair · gemini-2.0-flash

    new

    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
    <bos>
    -0.50
    grade
    -0.40
     Arhivirano
    -0.39
    rug
    -0.38
    tim
    -0.37
     len
    -0.36
    gr
    -0.36
     Meksiku
    -0.36
     grade
    -0.35
    llar
    -0.35
    POSITIVE LOGITS
     Efq
    0.66
    ^(@)
    0.57
     ſtate
    0.55
     Eſ
    0.54
     itſelf
    0.51
     myſelf
    0.50
     themſelves
    0.49
     purpoſe
    0.48
     Theſe
    0.47
     raiſ
    0.46
    Activations Density 0.381%

    No Known Activations