© 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. 6710
    Prev
    Next
    INDEX
    Explanations

    words related to water flow, drainage, and pollution

    oai_token-act-pair · gemini-2.0-flash

    water runoff

    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
    imageshack
    -0.51
     thẻ
    -0.50
    staticmethod
    -0.50
    ագրություններ
    -0.50
    zugehen
    -0.49
    GraphicsUnit
    -0.47
    erli
    -0.46
    COUVER
    -0.46
    circledR
    -0.45
    gewiesen
    -0.45
    POSITIVE LOGITS
    tonode
    0.61
    énario
    0.61
    ########.
    0.59
    CopyWith
    0.59
    actionMode
    0.57
    Халык
    0.56
     '{@
    0.55
    StoryboardSegue
    0.54
    IBar
    0.53
    stdc
    0.52
    Activations Density 3.205%

    No Known Activations