© 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. 5757
    Prev
    Next
    INDEX
    Explanations

    the characters "Ang", "aff", "cert", and other short tokens

    oai_token-act-pair · gemini-2.0-flash

    Ang

    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
    paka
    -0.46
    MERC
    -0.44
    UnusedPrivate
    -0.43
    rawQuery
    -0.43
     Merc
    -0.43
    IntoConstraints
    -0.41
    Exeunt
    -0.41
     MERC
    -0.41
     Consultez
    -0.41
     GNA
    -0.41
    POSITIVE LOGITS
     propOrder
    0.62
    GEBURTSDATUM
    0.60
     protoimpl
    0.57
    MemoryWarning
    0.56
    ftant
    0.54
     AssemblyTitle
    0.52
     voluto
    0.49
    ɚ
    0.49
    alow
    0.48
    urous
    0.48
    Activations Density 7.057%

    No Known Activations