© 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. 16344
    Prev
    Next
    INDEX
    Explanations

    academic citations and references

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     ISNI
    -0.67
     Efq
    -0.59
    windowFixed
    -0.57
    цезда
    -0.56
    Identyfik
    -0.55
     pleaſure
    -0.54
     uſed
    -0.54
     anſ
    -0.54
     houſe
    -0.52
    StoryboardSegue
    -0.52
    POSITIVE LOGITS
     e
    3.30
    e
    2.19
     eg
    1.62
    ｅ
    1.25
    eg
    1.15
     е
    1.13
    𝑒
    1.07
     i
    0.94
     eo
    0.92
     ee
    0.90
    Activations Density 13.526%

    No Known Activations