© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9268
    Prev
    Next
    INDEX
    Explanations

    words or short phrases describing negative states of being, like emotional or physical distress, or difficult actions involving tools.

    oai_token-act-pair · gemini-2.0-flash

    becoming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Efq
    -0.56
     Infórmanos
    -0.56
     gynhyrchwyd
    -0.55
     المعيارى
    -0.54
    ']))
    -0.54
    HasAnnotation
    -0.53
     estekak
    -0.52
    IndentedString
    -0.50
    UAGE
    -0.50
    migrationBuilder
    -0.50
    POSITIVE LOGITS
     become
    1.41
    Becoming
    1.40
     becoming
    1.40
     Becoming
    1.38
     became
    1.33
     becomes
    1.32
    become
    1.32
    becoming
    1.28
     Become
    1.28
    Become
    1.21
    Activations Density 3.009%

    No Known Activations