© 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. 15011
    Prev
    Next
    INDEX
    Explanations

    snippets of programming code or internet chat disclaimers in multiple languages

    oai_token-act-pair · gemini-2.0-flash

    Foreign 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
     how
    -3.02
     How
    -2.70
    How
    -2.63
    how
    -2.61
     what
    -2.33
     HOW
    -2.20
     why
    -2.20
    what
    -2.17
     What
    -2.16
    What
    -2.09
    POSITIVE LOGITS
    rawDesc
    0.54
    WriteBarrier
    0.54
     GetEnumerator
    0.46
    InstanceState
    0.45
    iNdEx
    0.45
     Oblast
    0.44
     BoxFit
    0.44
    cookieParser
    0.43
    enzie
    0.42
    lorette
    0.42
    Activations Density 3.376%

    No Known Activations