© 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. 13324
    Prev
    Next
    INDEX
    Explanations

    words that suggest a discussion, debate, or justification are taking place.

    oai_token-act-pair · 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
     say
    -2.13
     says
    -1.98
     said
    -1.80
    say
    -1.77
     Says
    -1.76
    says
    -1.73
    Says
    -1.68
    said
    -1.61
    Say
    -1.55
     saying
    -1.54
    POSITIVE LOGITS
    SBATCH
    0.58
    ẩu
    0.53
    getreten
    0.52
     SwitchCompat
    0.52
    ⓧ
    0.50
     otomatig
    0.49
    GraphicsUnit
    0.49
    oredCriteria
    0.48
     PopupWindow
    0.48
     li
    0.47
    Activations Density 4.283%

    No Known Activations