© 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. 12517
    Prev
    Next
    INDEX
    Explanations

    words and phrases talking about role playing games

    oai_token-act-pair · gemini-2.0-flash

    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
    rungsseite
    -0.60
    EDEFAULT
    -0.60
     שוליים
    -0.59
     createState
    -0.57
    ngOnInit
    -0.56
    webElementXpaths
    -0.54
     Wicidata
    -0.52
    bitField
    -0.52
    setContentView
    -0.51
    WriteLiteral
    -0.50
    POSITIVE LOGITS
     Shakspeare
    0.58
    িল
    0.52
    Nhưng
    0.49
     bekämp
    0.48
    trường
    0.48
     boletín
    0.48
    CompilerServices
    0.48
     Româ
    0.48
     Shaksp
    0.47
    angeran
    0.47
    Activations Density 1.949%

    No Known Activations