© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6946
    Prev
    Next
    INDEX
    Explanations

    sentences that talk about something staying the same

    oai_token-act-pair · gemini-2.0-flash

    remain

    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
    Lähteet
    -0.72
     resourceCulture
    -0.64
     հղումներ
    -0.56
     AssemblyCulture
    -0.55
    KommentareTeilen
    -0.50
     pretty
    -0.50
    gnore
    -0.49
     okuyayım
    -0.48
    MLLoader
    -0.48
    Aiheesta
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.56
    XmlAttribute
    0.52
    edly
    0.52
     onAnimation
    0.51
    MarshalTo
    0.51
    تفصیلات
    0.51
     urgently
    0.50
    Tikang
    0.50
    ModelSerializer
    0.50
     sogget
    0.50
    Activations Density 21.195%

    No Known Activations