© 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. 12347
    Prev
    Next
    INDEX
    Explanations

    bits of code, song lyrics, and mentions of death

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
    parsedMessage
    -0.66
    providedIn
    -0.61
    fillType
    -0.56
     externi
    -0.54
     bijzonder
    -0.54
    izr
    -0.53
    MockBean
    -0.52
     čierna
    -0.50
    expandindo
    -0.48
     fritas
    -0.48
    POSITIVE LOGITS
    IsContent
    0.62
    ⓧ
    0.59
    ://$
    0.55
    Xaml
    0.54
    ---|---|
    0.54
     AssemblyTitle
    0.54
     <<<<<<<<<<<<<<
    0.54
     ProtoMessage
    0.53
     OMIT
    0.53
    ویی
    0.53
    Activations Density 0.314%

    No Known Activations