© 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. 301
    Prev
    Next
    INDEX
    Explanations

    a combination of technical language used in scientific papers, nutrition and health-related observations, and political and policy discussions.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets or file paths

    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
     positions
    -1.00
     cases
    -0.97
     applications
    -0.93
     solutions
    -0.90
     situations
    -0.88
    Cases
    -0.87
     projects
    -0.87
     recipes
    -0.87
     titles
    -0.86
     Positions
    -0.86
    POSITIVE LOGITS
    /**
    0.79
     متعلقه
    0.72
     ModelExpression
    0.70
     "..\..\
    0.65
     estekak
    0.61
    SequentialGroup
    0.60
     dieux
    0.60
    fjspx
    0.59
    writerow
    0.57
    prnt
    0.57
    Activations Density 15.651%

    No Known Activations