© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4263
    Prev
    Next
    INDEX
    Explanations

    seemingly random characters in close proximity, or collocations which usually wouldn't be found together

    oai_token-act-pair · gemini-2.0-flash

    article text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    зам
    -0.47
    real
    -0.45
     k
    -0.44
     bay
    -0.42
     real
    -0.42
    abay
    -0.42
     Bay
    -0.41
     ka
    -0.41
    uskan
    -0.41
    염
    -0.41
    POSITIVE LOGITS
     InputDecoration
    0.67
    ⓧ
    0.66
    HasForeignKey
    0.64
    ]--;
    0.64
    حياته
    0.63
     ――――――――
    0.63
    sidemargin
    0.62
     Seeder
    0.62
     "..\..\..\
    0.61
    ParallelGroup
    0.60
    Activations Density 0.462%

    No Known Activations