© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12053
    Prev
    Next
    INDEX
    Explanations

    code syntax relating to structs and memory addresses

    oai_token-act-pair · gemini-2.0-flash

    archaic English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    bb
    -0.54
    dt
    -0.53
    cc
    -0.52
    js
    -0.50
    ff
    -0.50
    pp
    -0.50
    rt
    -0.50
    ft
    -0.50
    tt
    -0.49
    zt
    -0.49
    POSITIVE LOGITS
     itſelf
    1.08
     themſelves
    0.93
     ſeveral
    0.91
     iſt
    0.89
     ſtate
    0.87
     myſelf
    0.85
     preſent
    0.85
    wiſe
    0.85
     faſt
    0.85
    ſelves
    0.83
    Activations Density 2.917%

    No Known Activations