© 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. 4601
    Prev
    Next
    INDEX
    Explanations

    words related to tides and ocean currents

    oai_token-act-pair · gemini-2.0-flash

    weather/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
     Chwiliwch
    -0.70
    ]")]
    -0.69
    ApiModelProperty
    -0.68
     bParam
    -0.64
    StoryboardSegue
    -0.63
     Exacts
    -0.63
    SourceChecksum
    -0.62
    enumi
    -0.62
    rawDesc
    -0.61
    
    -0.61
    POSITIVE LOGITS
    ThroughAttribute
    0.52
     Wicidata
    0.47
     échou
    0.46
     ed
    0.45
    زد
    0.45
    pegno
    0.44
     broke
    0.43
    idine
    0.42
     σχέ
    0.42
    WRP
    0.41
    Activations Density 1.692%

    No Known Activations