© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12451
    Prev
    Next
    INDEX
    Explanations

    sentences describing planning and carrying out activities involving children and food

    oai_token-act-pair · gemini-2.0-flash

    hang/hung

    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
     hunger
    -1.32
     Hunger
    -1.29
     hungry
    -1.25
    Hunger
    -1.13
     thirsty
    -1.12
     Hungry
    -1.10
    Hungry
    -1.09
    hunger
    -1.06
     starving
    -1.03
     starved
    -1.00
    POSITIVE LOGITS
     hung
    0.78
     hang
    0.74
     hangs
    0.70
    hang
    0.65
    Hang
    0.59
     HANG
    0.55
     Hang
    0.54
     hanging
    0.51
    hung
    0.50
     hanged
    0.50
    Activations Density 2.414%

    No Known Activations