© 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. 4793
    Prev
    Next
    INDEX
    Explanations

    institutional language, especially names of organizations and schools

    oai_token-act-pair · gemini-2.0-flash

    Organizations

    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
     Audiodateien
    -0.53
    }}_
    -0.50
    SharedDtor
    -0.48
     bege
    -0.45
    npmjs
    -0.44
    }}^
    -0.44
    ful
    -0.43
    addGroup
    -0.42
    Bibliograf
    -0.40
    ezy
    -0.40
    POSITIVE LOGITS
     متعلقه
    1.00
    OptionsMenu
    0.67
     AssemblyCompany
    0.65
    èdia
    0.60
    rawDesc
    0.60
     IBOutlet
    0.59
    семь
    0.58
    COUVER
    0.58
    StructEnd
    0.57
    orters
    0.56
    Activations Density 11.428%

    No Known Activations