© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8393
    Prev
    Next
    INDEX
    Explanations

    a mix of things including: place names, software terminology, medical terminology, formatting and percentage symbols

    oai_token-act-pair · gemini-2.0-flash

    Code and database entries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     m
    -0.80
     mm
    -0.66
     ma
    -0.62
     mes
    -0.60
     mat
    -0.58
     mc
    -0.56
    master
    -0.56
     md
    -0.56
     ms
    -0.56
     mo
    -0.56
    POSITIVE LOGITS
     Μ
    0.62
    Ｍ
    0.58
     More
    0.57
    Μ
    0.54
     Más
    0.53
    ucket
    0.53
    ModelSerializer
    0.52
     Ма
    0.52
     Meningkatkan
    0.51
    ftagPool
    0.51
    Activations Density 3.283%

    No Known Activations