© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7321
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with shark diving

    oai_token-act-pair · gemini-2.0-flash

    Diving and ocean activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Espèce
    -0.59
    migrationBuilder
    -0.58
    ffindor
    -0.57
    ISupport
    -0.54
     scatola
    -0.53
     Majefty
    -0.53
     provisoire
    -0.52
    scalatest
    -0.52
    knapp
    -0.51
     recibo
    -0.50
    POSITIVE LOGITS
    enumi
    0.64
    anzen
    0.47
    Filmografie
    0.47
     CanadaChoose
    0.47
    /**
    0.46
    NOST
    0.46
     Ka
    0.46
     Channing
    0.45
     Vega
    0.44
     SPO
    0.44
    Activations Density 1.202%

    No Known Activations