© 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. 15990
    Prev
    Next
    INDEX
    Explanations

    legal citations and references

    oai_token-act-pair · gemini-2.0-flash

    names

    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
     Esau
    -0.79
     Charlemagne
    -0.77
     Benzema
    -0.77
     Nemesis
    -0.75
     Maradona
    -0.74
     Mugabe
    -0.74
     Molière
    -0.73
     Marconi
    -0.73
     Vivaldi
    -0.73
     Medea
    -0.73
    POSITIVE LOGITS
     Whit
    0.68
     Feld
    0.65
     Salt
    0.65
     Hin
    0.63
     Bed
    0.63
     Lind
    0.62
     Gal
    0.61
    iſe
    0.61
    iſt
    0.61
     Fitz
    0.61
    Activations Density 5.416%

    No Known Activations