© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12459
    Prev
    Next
    INDEX
    Explanations

    named places

    oai_token-act-pair · gemini-2.0-flash

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ANTLR
    -0.65
    ActionPerformed
    -0.53
     оригіналу
    -0.50
    FontOfSize
    -0.50
    exitRule
    -0.49
     Timor
    -0.48
    mogat
    -0.47
     defaultValue
    -0.47
    askan
    -0.47
    quelize
    -0.47
    POSITIVE LOGITS
     itſelf
    0.86
     myſelf
    0.76
    Хьажоргаш
    0.71
     ſtre
    0.69
     chofe
    0.67
     raiſ
    0.66
    حياته
    0.66
    martre
    0.65
    hoeddwyd
    0.65
    ſelves
    0.65
    Activations Density 0.833%

    No Known Activations