© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8485
    Prev
    Next
    INDEX
    Explanations

    a mixture of common french, spanish and technical terms

    oai_token-act-pair · gemini-2.0-flash

    code snippets/foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     of
    -0.80
    IUrlHelper
    -0.74
     يتيمه
    -0.74
     tartalomajánló
    -0.68
    PositiveButton
    -0.65
    ftagPool
    -0.65
     vPvB
    -0.64
    出版年
    -0.63
    InstanceState
    -0.63
    aarrggbb
    -0.61
    POSITIVE LOGITS
     ses
    0.90
     sus
    0.88
    sus
    0.75
     tus
    0.74
     Sus
    0.68
     vos
    0.67
    Sus
    0.66
     sina
    0.64
    KommentareTeilen
    0.61
     dina
    0.59
    Activations Density 0.843%

    No Known Activations