© 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. 5500
    Prev
    Next
    INDEX
    Explanations

    the word "Lake" and words associated with it

    oai_token-act-pair · gemini-2.0-flash

    Lake

    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
     désolés
    -0.52
     lakes
    -0.48
     Lakes
    -0.47
    ny
    -0.47
     Founding
    -0.45
    Espèce
    -0.44
     congratulate
    -0.43
    CAUTIONS
    -0.43
     pylori
    -0.43
     founding
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.65
    riwal
    0.56
    PhysRev
    0.56
    +:+
    0.56
    uary
    0.53
    <?
    0.53
    AxisAlignment
    0.52
    icium
    0.51
    apult
    0.51
    digkeit
    0.50
    Activations Density 0.884%

    No Known Activations