© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10408
    Prev
    Next
    INDEX
    Explanations

    geographical references including cardinal directions

    oai_token-act-pair · gemini-2.0-flash

    directions

    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
    RuleContext
    -0.72
     onPostExecute
    -0.55
    ámico
    -0.50
    صحاب
    -0.50
    writerow
    -0.48
    ✎
    -0.47
     المعيارى
    -0.47
    ngOnInit
    -0.47
    udahkan
    -0.47
     titulaire
    -0.47
    POSITIVE LOGITS
    RegistryLite
    0.81
    Cyfeiriadau
    0.69
     Baillargeon
    0.63
     للاسماء
    0.59
     resourceCulture
    0.59
    webElementGuid
    0.57
    lapsingToolbar
    0.57
    ControllerAdvice
    0.57
    Gön
    0.56
    Становништво
    0.56
    Activations Density 1.362%

    No Known Activations