© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12341
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ing' that can be interpreted as an activity currently underway

    oai_token-act-pair · gemini-2.0-flash

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     delivering
    -1.10
     getting
    -1.07
     trying
    -1.05
     providing
    -1.04
     accessing
    -1.03
     taking
    -1.03
     preparing
    -1.02
     doing
    -1.02
     being
    -1.01
     making
    -1.01
    POSITIVE LOGITS
     Eſ
    0.71
     Hacking
    0.67
    aling
    0.66
     ſche
    0.65
    ning
    0.65
    ịch
    0.64
     Reſ
    0.64
    PING
    0.63
    hlung
    0.63
    ening
    0.63
    Activations Density 2.678%

    No Known Activations