© 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. 152
    Prev
    Next
    INDEX
    Explanations

    language about planning and building infrastructure

    oai_token-act-pair · gemini-2.0-flash

    Things being developed

    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
     AssemblyProduct
    -0.66
    expandindo
    -0.59
    الإنجليزية
    -0.58
     ivelany
    -0.53
    تقاوى
    -0.51
     Roskov
    -0.48
    Bibliografía
    -0.48
     "}";
    -0.47
    RTEE
    -0.47
     kaynağından
    -0.47
    POSITIVE LOGITS
    ftagPool
    0.72
    bootstrapcdn
    0.55
    AddHtmlAttribute
    0.53
    managing
    0.53
     Driving
    0.53
     driving
    0.53
    TabLayout
    0.52
    Driving
    0.51
    driving
    0.49
     Theſe
    0.49
    Activations Density 11.758%

    No Known Activations