© 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. 5696
    Prev
    Next
    INDEX
    Explanations

    terms from a language other than English related to terms of service and privacy

    oai_token-act-pair · gemini-2.0-flash

    Account creation/web content

    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
    KommentareTeilen
    -1.04
    Diweddarwch
    -0.85
     виправивши
    -0.83
     مشين
    -0.82
    DockStyle
    -0.81
     BoxFit
    -0.80
    httphttps
    -0.80
    tagHelperRunner
    -0.79
     beginnetje
    -0.77
     EconPapers
    -0.76
    POSITIVE LOGITS
    tomcat
    0.42
    minecraft
    0.42
    xia
    0.41
    laga
    0.40
     pull
    0.40
    lia
    0.40
     dép
    0.39
     biztos
    0.39
     Boucher
    0.39
    pull
    0.38
    Activations Density 0.329%

    No Known Activations