© 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. 3371
    Prev
    Next
    INDEX
    Explanations

    informal conversation or dialogue involving personal experiences

    oai_token-act-pair · gemini-2.0-flash

    was

    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
     many
    -1.17
    many
    -1.07
     Many
    -1.03
    Many
    -1.03
     MANY
    -1.02
     muchos
    -0.94
     rather
    -0.94
     muitos
    -0.94
     very
    -0.93
     truly
    -0.93
    POSITIVE LOGITS
    OGND
    0.79
    TagHelper
    0.79
    InjectAttribute
    0.78
    findpost
    0.78
     تضيفلها
    0.78
    webElement
    0.75
    TestingModule
    0.74
     '{@
    0.71
    исленность
    0.70
    ,:),
    0.70
    Activations Density 2.575%

    No Known Activations