© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3504
    Prev
    Next
    INDEX
    Explanations

    words related to seafood and fish

    oai_token-act-pair · gemini-2.0-flash

    Seafood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    gantung
    -0.54
     calendriers
    -0.52
    TabStop
    -0.48
     stof
    -0.47
    choly
    -0.47
     continuant
    -0.44
     delo
    -0.44
     '\\;'
    -0.43
    __(/*!
    -0.43
     surla
    -0.43
    POSITIVE LOGITS
     fish
    1.31
    <bos>
    1.22
     fishes
    1.16
    fish
    1.10
    Fish
    1.09
     Fish
    1.06
     FISH
    0.98
    fishes
    0.97
    lapia
    0.91
     Fishes
    0.89
    Activations Density 0.380%

    No Known Activations