© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2371
    Prev
    Next
    INDEX
    Explanations

    mentions of systemic and legal issues as well as some personal pronouns.

    oai_token-act-pair · gemini-2.0-flash

    says "no"

    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
     متعلقه
    -0.63
     utafiti
    -0.63
    如果不是
    -0.60
    要不是
    -0.59
    +#+#
    -0.57
    SourceChecksum
    -0.55
    rawDesc
    -0.55
     pinulongan
    -0.54
    __;
    -0.53
    occa
    -0.52
    POSITIVE LOGITS
     no
    3.70
    no
    2.89
    No
    2.20
     NO
    2.17
    NO
    1.98
     No
    1.98
     kein
    1.34
     keine
    1.28
     нет
    1.23
     nof
    1.22
    Activations Density 6.701%

    No Known Activations