© 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. 8823
    Prev
    Next
    INDEX
    Explanations

    numbers, especially currency amounts and scientific article references

    oai_token-act-pair · gemini-2.0-flash

    Numbers and symbols

    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
     originais
    -0.41
     femininas
    -0.40
    seamnă
    -0.40
     brancas
    -0.39
     complètes
    -0.38
     engraçadas
    -0.37
     تضيفلها
    -0.36
     solteiro
    -0.35
     enfans
    -0.35
     preuves
    -0.35
    POSITIVE LOGITS
    ÍC
    0.59
     Stodd
    0.59
    IMAS
    0.57
    ITUDE
    0.57
    IENTE
    0.56
    Carriera
    0.55
    IVOS
    0.55
     pulumi
    0.55
    renos
    0.54
    ÍN
    0.54
    Activations Density 16.087%

    No Known Activations