© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10869
    Prev
    Next
    INDEX
    Explanations

    words related to mechanical objects and activities like fixing a car or bike.

    oai_token-act-pair · gemini-2.0-flash

    Vehicle/machine components

    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
     Numerade
    -0.69
    matchCondition
    -0.67
    imageshack
    -0.60
    windowFixed
    -0.58
    dafx
    -0.58
    енча
    -0.53
    ArrowToggle
    -0.52
    GraphicsUnit
    -0.51
    tagHelperRunner
    -0.51
     Fuel
    -0.51
    POSITIVE LOGITS
    RectangleBorder
    0.66
    сну
    0.45
    toplankton
    0.44
     Pote
    0.44
    ềm
    0.43
    hyrchwyd
    0.42
     nonUne
    0.42
    metology
    0.42
    '&:
    0.42
    MenuInflater
    0.42
    Activations Density 1.523%

    No Known Activations