© 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. 12348
    Prev
    Next
    INDEX
    Explanations

    StackOverflow posts including code related to Java and .NET.

    oai_token-act-pair · gemini-2.0-flash

    Java and .NET

    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
    #+#
    -0.55
    Placed
    -0.53
    Carriera
    -0.49
     Reim
    -0.48
     Ample
    -0.46
    𝗞
    -0.45
    Posted
    -0.45
    ктан
    -0.44
    ema
    -0.44
    estinations
    -0.44
    POSITIVE LOGITS
    ⓧ
    0.61
    таратура
    0.56
    serviceWorker
    0.56
    noinspection
    0.56
    adple
    0.56
     SqlCommand
    0.56
    ImGui
    0.56
    SqlCommand
    0.56
    DataGridView
    0.55
    phrag
    0.55
    Activations Density 5.348%

    No Known Activations