© 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. 14296
    Prev
    Next
    INDEX
    Explanations

    seemingly randomly a few words from a sentence

    oai_token-act-pair · 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
    Enllaces
    -0.58
    ArgsConstructor
    -0.57
     pinulongan
    -0.52
    anches
    -0.50
     lyre
    -0.49
    يكب
    -0.48
    lapsingToolbar
    -0.48
     prosecuting
    -0.47
     rotors
    -0.47
     Provid
    -0.47
    POSITIVE LOGITS
    <bos>
    0.89
     оригіналу
    0.67
    Tikang
    0.64
     ویکی‌پدی
    0.60
    enterOuterAlt
    0.60
    ApiModelProperty
    0.59
    MigrationBuilder
    0.59
    تقاوى
    0.58
    saraba
    0.57
     '\\;'
    0.57
    Activations Density 12.032%

    No Known Activations