© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10349
    Prev
    Next
    INDEX
    Explanations

    references to God and faith

    oai_token-act-pair · gemini-2.0-flash

    religion/god

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    存于互联网档案馆
    -0.46
     Laurens
    -0.44
    sscanf
    -0.42
     chez
    -0.42
    parseLong
    -0.41
    fluidic
    -0.40
     methylene
    -0.40
     rien
    -0.40
    älä
    -0.39
    gency
    -0.38
    POSITIVE LOGITS
     AspNetCore
    0.73
    |}{$
    0.73
    Hozzáférés
    0.69
    Jereo
    0.64
     @"/
    0.64
     SqlParameter
    0.63
    RegressionTest
    0.63
    djangoproject
    0.62
     RNG
    0.60
     Roskov
    0.60
    Activations Density 0.393%

    No Known Activations