© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1117
    Prev
    Next
    INDEX
    Explanations

    code-related keywords with a preference for JSON.

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     and
    -2.09
     or
    -1.15
    and
    -0.96
     but
    -0.82
    和
    -0.81
    or
    -0.77
     which
    -0.74
    และ
    -0.72
     with
    -0.71
     và
    -0.68
    POSITIVE LOGITS
     utafitiHapana
    0.68
     igång
    0.53
    @",
    0.53
    tır
    0.52
    ++
    
    0.52
     iArr
    0.51
    _
    
    0.50
    {!
    0.49
    Und
    0.48
     varandra
    0.48
    Activations Density 5.387%

    No Known Activations