© 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. 14622
    Prev
    Next
    INDEX
    Explanations

    physics papers and journals with an emphasis on renormalization and high energy physics

    oai_token-act-pair · gemini-2.0-flash

    research papers

    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
     cherchés
    -0.84
    estacks
    -0.63
    awtextra
    -0.54
     Roskov
    -0.51
     Vedi
    -0.49
     Référence
    -0.48
     beginnetje
    -0.48
    TestingModule
    -0.47
    principalTable
    -0.45
    TAINMENT
    -0.45
    POSITIVE LOGITS
     '+':
    0.54
     &___
    0.54
     hâte
    0.53
    ülerin
    0.53
    RegistryLite
    0.53
     ProtoMessage
    0.52
    }%
    0.51
     Vikipedi
    0.51
    iprot
    0.50
     Hinton
    0.50
    Activations Density 6.374%

    No Known Activations