© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1987
    Prev
    Next
    INDEX
    Explanations

    years

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     StatefulWidget
    -0.50
    ReusableCell
    -0.48
    TestingModule
    -0.47
    ChildScrollView
    -0.45
     GenerationType
    -0.45
    ########.
    -0.44
    setContentView
    -0.43
     Chwiliwch
    -0.43
    =?";
    -0.43
     egret
    -0.43
    POSITIVE LOGITS
    UVWXYZ
    0.68
     traités
    0.64
    ANC
    0.57
    országban
    0.56
    erover
    0.56
    NZ
    0.56
    hésite
    0.55
     commerciales
    0.55
    εβ
    0.55
    Zacks
    0.54
    Activations Density 7.404%

    No Known Activations