© 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. 6369
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly those involving user and database interactions

    oai_token-act-pair · gemini-2.0-flash

    user

    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
    -1.13
    EndGlobalSection
    -1.01
     CreateTagHelper
    -0.96
    Portale
    -0.92
    CppMethod
    -0.91
    ModelAdmin
    -0.85
    .*")]
    -0.82
     protoimpl
    -0.81
    jsxFileName
    -0.81
    rungsseite
    -0.80
    POSITIVE LOGITS
    ip
    0.44
    ars
    0.41
    data
    0.41
    ロール
    0.39
     boc
    0.39
    ak
    0.38
    LEV
    0.38
    വ
    0.38
    O
    0.38
     piccolo
    0.38
    Activations Density 2.017%

    No Known Activations