© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15040
    Prev
    Next
    INDEX
    Explanations

    text discussing South African immigration policies and related information

    oai_token-act-pair · gemini-2.0-flash

    reciprocal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    帖最后由
    -0.93
    出版年
    -0.68
     protoimpl
    -0.58
    ;">
    -0.56
    webElementGuid
    -0.55
    SourceChecksum
    -0.53
     }{@
    -0.52
    ngdoc
    -0.52
    InputTagHelper
    -0.50
     considérons
    -0.50
    POSITIVE LOGITS
    IUrlHelper
    0.59
     Eury
    0.56
     solare
    0.55
     Etrus
    0.54
    iedy
    0.54
     Mercantile
    0.52
     Silurian
    0.52
     Esau
    0.52
     Oggi
    0.52
    Джерела
    0.51
    Activations Density 3.777%

    No Known Activations