© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14631
    Prev
    Next
    INDEX
    Explanations

    words describing geology, water, light, and natural landscapes

    oai_token-act-pair · gemini-2.0-flash

    creating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    клопе
    -0.69
    ----</
    -0.54
    SPJ
    -0.53
    (!__
    -0.52
    tvguidetime
    -0.52
    anele
    -0.52
    SuppressLint
    -0.51
    Personendaten
    -0.50
    ReusableCell
    -0.50
     FormsModule
    -0.49
    POSITIVE LOGITS
     beginnetje
    0.56
     terem
    0.52
     للمعارف
    0.50
    גרפיה
    0.50
     tilbud
    0.49
     prova
    0.47
    ATS
    0.47
    rahat
    0.47
     cruce
    0.47
     getChild
    0.46
    Activations Density 0.891%

    No Known Activations