© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1697
    Prev
    Next
    INDEX
    Explanations

    references to Allah and religious concepts

    oai_token-act-pair · gemini-2.0-flash

    Allah

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    +#+#
    -0.76
     Roskov
    -0.66
     MenuView
    -0.65
    ClientSize
    -0.64
    aarrggbb
    -0.64
     ivelany
    -0.61
    <!--[
    -0.56
    webElement
    -0.55
     pinulongan
    -0.55
    IsMutable
    -0.52
    POSITIVE LOGITS
    nsch
    0.53
    وث
    0.52
    EVER
    0.52
    钥
    0.51
    FormTagHelper
    0.50
    hima
    0.49
    orable
    0.49
    esian
    0.49
    اریخ
    0.47
    xious
    0.47
    Activations Density 0.081%

    No Known Activations