© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11620
    Prev
    Next
    INDEX
    Explanations

    words related to difficulties and inner struggles, but also words of encouragement, inspiration, and community.

    oai_token-act-pair · gemini-2.0-flash

    expression of thoughts

    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
    hoppers
    -0.58
    abestanden
    -0.58
    hopper
    -0.57
    ględ
    -0.57
    Datuak
    -0.54
     AppComponent
    -0.53
    DMETHOD
    -0.52
    ppelin
    -0.50
    annica
    -0.49
     चीज़ों
    -0.48
    POSITIVE LOGITS
    UpInside
    0.54
    はじめに
    0.51
    AccessorTable
    0.51
     Monfieur
    0.50
     uſed
    0.50
    يميديا
    0.49
    estinian
    0.49
    <bos>
    0.48
    ReusableCell
    0.48
    ...@
    0.48
    Activations Density 14.347%

    No Known Activations