© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3312
    Prev
    Next
    INDEX
    Explanations

    scientific publication references

    oai_token-act-pair · gemini-2.0-flash

    scientific publications

    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
     (
    -0.47
     t
    -0.42
     rem
    -0.40
     s
    -0.40
     ax
    -0.39
     shut
    -0.39
     bra
    -0.39
     p
    -0.38
     sti
    -0.37
     ro
    -0.36
    POSITIVE LOGITS
     étoit
    0.90
     feroit
    0.88
     pouvoit
    0.85
     enfans
    0.85
     auroit
    0.85
     avoient
    0.83
     specchio
    0.81
     étoient
    0.80
     asiatique
    0.79
     religieuses
    0.79
    Activations Density 3.365%

    No Known Activations