© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13377
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to job positions, organizations, and titles

    oai_token-act-pair · gemini-2.0-flash

    technical and code documentation

    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
     Owner
    -1.34
     Manager
    -1.33
     Writer
    -1.30
     Operator
    -1.30
    Writer
    -1.29
     owner
    -1.28
     Builder
    -1.26
     Producer
    -1.26
    Producer
    -1.25
     Lecturer
    -1.22
    POSITIVE LOGITS
    UnsafeEnabled
    0.52
    tagHelperRunner
    0.50
     Wicidata
    0.46
    tvguidetime
    0.42
    posedge
    0.41
     jSON
    0.41
    ниципа
    0.40
     هيا
    0.39
    endphp
    0.38
    ź
    0.38
    Activations Density 3.815%

    No Known Activations