© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6579
    Prev
    Next
    INDEX
    Explanations

    positive sentiment language with a personal connection.

    oai_token-act-pair · gemini-2.0-flash

    positive feelings, purpose

    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
     Hearst
    -0.54
    stdafx
    -0.53
     rehabilitate
    -0.52
    closedir
    -0.52
     Italijanski
    -0.52
    はじめに
    -0.50
     Visconti
    -0.50
     """",
    -0.49
     défend
    -0.49
     transposition
    -0.49
    POSITIVE LOGITS
     iprot
    0.58
     GRAT
    0.54
     patience
    0.52
    مصادر
    0.49
    KeySpec
    0.48
     purpose
    0.48
     cache
    0.45
     stability
    0.45
    purpose
    0.45
     perspective
    0.44
    Activations Density 1.717%

    No Known Activations