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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11587
    Prev
    Next
    INDEX
    Explanations

    words used in marketing materials discussing products or studies

    oai_token-act-pair · gemini-2.0-flash

    Reports and acknowledgements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    raeli
    -0.49
    ịt
    -0.48
    ẾT
    -0.46
    ্ড
    -0.46
     hjæl
    -0.45
    FECT
    -0.43
     mã
    -0.42
    purl
    -0.41
     elliptic
    -0.41
    SuppressLint
    -0.41
    POSITIVE LOGITS
    MessageTagHelper
    0.68
    oa̍t
    0.65
    TypedDataSet
    0.64
    +:+
    0.63
     HasFactory
    0.63
     AssemblyCulture
    0.63
     invokingState
    0.59
    rrggbb
    0.59
    Kjelder
    0.59
    下载附件
    0.57
    Activations Density 36.718%

    No Known Activations