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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14183
    Prev
    Next
    INDEX
    Explanations

    uses quotation marks and appears to activate on writing and speech, or opinions and assertions about news, code or scripture

    oai_token-act-pair · gemini-2.0-flash

    code and legal text

    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
     והוא
    -0.82
    ConstraintMaker
    -0.71
     并
    -0.68
     iar
    -0.58
    脚注の使い方
    -0.56
    然後
    -0.55
     並
    -0.54
    并将
    -0.54
    而且
    -0.53
     usw
    -0.52
    POSITIVE LOGITS
     and
    1.81
     والأ
    0.75
    และ
    0.74
     والم
    0.73
     &
    0.69
     \&
    0.67
    和
    0.67
     والس
    0.67
    -,
    0.63
    および
    0.63
    Activations Density 25.155%

    No Known Activations