© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1510
    Prev
    Next
    INDEX
    Explanations

    mentions of a region or local area with accompanying objects or services

    oai_token-act-pair · gemini-2.0-flash

    local

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     local
    -0.97
    Local
    -0.94
     Local
    -0.94
    local
    -0.90
     LOCAL
    -0.87
    LOCAL
    -0.85
     lokalen
    -0.80
    getLocal
    -0.79
     locally
    -0.79
     locaux
    -0.77
    POSITIVE LOGITS
    <bos>
    0.85
    WindowConstants
    0.48
    osoba
    0.47
     وجود
    0.47
    ftc
    0.46
     تانيه
    0.40
    ண்டும்
    0.40
    >>()
    0.40
     ✭✭
    0.40
    Charset
    0.39
    Activations Density 15.778%

    No Known Activations