© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13065
    Prev
    Next
    INDEX
    Explanations

    words related to project management and design

    oai_token-act-pair · gemini-2.0-flash

    construction and planning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    الدراسه
    -0.52
    kloped
    -0.44
     kunder
    -0.41
     na
    -0.41
    Zen
    -0.40
    рун
    -0.40
     Zen
    -0.39
    wa
    -0.39
    iente
    -0.39
     companhia
    -0.39
    POSITIVE LOGITS
     myſelf
    0.96
     pleaſure
    0.93
     Majefty
    0.88
     Monfieur
    0.87
     purpoſe
    0.84
     juſ
    0.83
     ſche
    0.83
     defire
    0.78
     becauſe
    0.78
     ſtand
    0.77
    Activations Density 1.692%

    No Known Activations