© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5570
    Prev
    Next
    INDEX
    Explanations

    words related to laws and accusing someone of something.

    oai_token-act-pair · gemini-2.0-flash

    code related information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     of
    -1.73
    of
    -1.02
    Of
    -0.75
     của
    -0.74
     Of
    -0.71
    tof
    -0.69
    ของ
    -0.69
     OF
    -0.66
     של
    -0.64
    ofd
    -0.60
    POSITIVE LOGITS
    évaluateur
    1.11
    AddTagHelper
    1.00
    AsUp
    0.97
     autorytatywna
    0.93
    ⓧ
    0.90
    Obrázky
    0.88
    Personendaten
    0.88
    AddHtmlAttribute
    0.85
     CreateTagHelper
    0.83
    GOTREF
    0.82
    Activations Density 1.502%

    No Known Activations