Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1218
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to regions, countries, dialects, ethnicities, and languages.

    oai_token-act-pair · gemini-2.0-flash

    Malay

    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
    RectangleBorder
    -0.61
     pinulongan
    -0.59
    rungsseite
    -0.58
     PhpStorm
    -0.57
    Composable
    -0.57
    EndGlobalSection
    -0.57
    })).
    -0.56
    ItemBackground
    -0.55
    fhir
    -0.55
    AutoScaleMode
    -0.54
    POSITIVE LOGITS
    +#+
    0.57
     cober
    0.51
     CreateTagHelper
    0.47
    dicionado
    0.46
     FetchType
    0.46
     endowments
    0.45
     mengenakan
    0.45
    rientes
    0.44
    aplic
    0.43
    postdata
    0.43
    Activations Density 27.835%

    No Known Activations