© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5650
    Prev
    Next
    INDEX
    Explanations

    mentions of "Fort"

    np_token-act-pair-logits · gpt-4o-mini

    the word "Fort" at the start of a place name

    oai_token-act-pair · gemini-2.0-flash

    Fort

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    tagHelperRunner
    -0.65
     JAXBElement
    -0.60
     arşivlendi
    -0.57
     Porn
    -0.55
     EconPapers
    -0.54
    ftagPool
    -0.54
     finite
    -0.52
    طلحات
    -0.51
     Urbana
    -0.50
    XmlAccessType
    -0.50
    POSITIVE LOGITS
    DNEY
    0.57
    الإنجليزية
    0.56
    etheless
    0.53
    ssystem
    0.53
     getRule
    0.52
    InjectAttribute
    0.51
     iNdEx
    0.50
    먹
    0.50
    `;
    0.50
    Funktion
    0.48
    Activations Density 0.088%

    No Known Activations