© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5763
    Prev
    Next
    INDEX
    Explanations

    citations of academic publications

    oai_token-act-pair · gemini-2.0-flash

    edition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     disclosure
    -0.82
     disclosures
    -0.79
     disclosed
    -0.78
     disclose
    -0.72
     Disclosure
    -0.71
     discloses
    -0.69
     disclosing
    -0.66
    seamnă
    -0.61
    disclosure
    -0.61
    Scorecard
    -0.59
    POSITIVE LOGITS
    +:+
    0.84
     незавершена
    0.73
    fjspx
    0.73
     Edition
    0.69
     edition
    0.60
     EDITION
    0.57
    edition
    0.56
    Edition
    0.56
    /**
    0.54
     edición
    0.53
    Activations Density 1.113%

    No Known Activations