© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15474
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to research, strategy, and numerical targets

    oai_token-act-pair · gemini-2.0-flash

    Business/study aims

    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
    LabelTagHelper
    -0.62
    istoitu
    -0.61
    glClear
    -0.59
     informée
    -0.59
     mergeFrom
    -0.54
     tormenta
    -0.52
    RegistryLite
    -0.50
    addGap
    -0.50
     høre
    -0.50
     soaking
    -0.49
    POSITIVE LOGITS
    bukkit
    0.63
    astru
    0.53
    GIH
    0.53
    Assured
    0.50
     ves
    0.48
    ItemBackground
    0.47
     EconPapers
    0.46
    withIdentifier
    0.45
    /**/*.
    0.45
    άνι
    0.45
    Activations Density 12.046%

    No Known Activations