© 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. 11758
    Prev
    Next
    INDEX
    Explanations

    words with some cultural (often middle eastern) or historical aspect that may be a name or location

    oai_token-act-pair · gemini-2.0-flash

    Islamic themes

    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
     Monfieur
    -0.74
    COUVER
    -0.72
     Jefus
    -0.69
    __':
    -0.68
     bezeichneter
    -0.68
     tartalomajánló
    -0.65
     Anſ
    -0.64
    __":
    -0.63
     <",
    -0.62
    helial
    -0.62
    POSITIVE LOGITS
     famí
    0.49
    parsedMessage
    0.47
    kla
    0.45
     resourceCulture
    0.43
     hyvin
    0.43
     gün
    0.42
    .
    0.41
    providedIn
    0.41
    arch
    0.41
    כל
    0.41
    Activations Density 7.927%

    No Known Activations