© 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. 4710
    Prev
    Next
    INDEX
    Explanations

    terms related to community and waste management

    oai_token-act-pair · gemini-2.0-flash

    Noun suffixes

    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
     Commencez
    -0.53
    usr
    -0.51
    ьаж
    -0.51
     nakalista
    -0.51
    quelize
    -0.51
     коды
    -0.51
    vej
    -0.50
    ēju
    -0.49
     gehört
    -0.49
     collecte
    -0.48
    POSITIVE LOGITS
    GraphicsUnit
    0.58
     himo
    0.46
    تقاوى
    0.43
     Buddhists
    0.43
     مرئيه
    0.42
     Buddhist
    0.42
    ATURE
    0.42
     Thebes
    0.42
    tschafts
    0.41
    RunAsync
    0.41
    Activations Density 7.579%

    No Known Activations