© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15375
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to personal experiences/reminiscence and thought processes.

    oai_token-act-pair · gemini-2.0-flash

    Memories

    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
     الرياضيه
    -0.85
     متعلقه
    -0.74
    MigrationBuilder
    -0.73
     estekak
    -0.68
     ComVisible
    -0.65
     кӀ
    -0.65
    béco
    -0.60
     zvuky
    -0.60
    tagHelperRunner
    -0.59
    errHandler
    -0.59
    POSITIVE LOGITS
    VideoCapture
    0.57
     fresh
    0.57
    fresh
    0.51
     FRESH
    0.50
    transQ
    0.50
    ecin
    0.47
     Platt
    0.47
     fresher
    0.45
     inde
    0.44
     Penh
    0.44
    Activations Density 2.484%

    No Known Activations