© 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. 3583
    Prev
    Next
    INDEX
    Explanations

    the word "sea"

    oai_token-act-pair · gemini-2.0-flash

    sea

    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
    -0.72
    typeorm
    -0.70
    argout
    -0.68
    nestjs
    -0.63
    ContentAsync
    -0.63
    resizable
    -0.60
     Chwiliwch
    -0.59
     Firearms
    -0.57
    ArgsConstructor
    -0.56
    Зноскі
    -0.56
    POSITIVE LOGITS
    Legături
    0.46
     muualla
    0.45
    GraphicsUnit
    0.42
    IUrlHelper
    0.42
    g
    0.41
    ))));
    0.41
    ÚBL
    0.41
     inter
    0.40
    +:+
    0.40
     g
    0.40
    Activations Density 0.801%

    No Known Activations