© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16031
    Prev
    Next
    INDEX
    Explanations

    mentions of 'you' and 'the'

    oai_token-act-pair · gemini-2.0-flash

    code or technology

    np_max-act-logits · gemini-2.0-flash

    say "verbs"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     estimate
    -0.87
     act
    -0.81
     report
    -0.81
     figure
    -0.77
     measure
    -0.77
    measure
    -0.75
    estimate
    -0.73
    report
    -0.73
     attempt
    -0.70
     Estimate
    -0.70
    POSITIVE LOGITS
     MainAxisSize
    0.77
    fjspx
    0.68
    NameInMap
    0.62
    SBATCH
    0.61
    ISupport
    0.59
    onActivityResult
    0.59
     esternos
    0.57
    iastes
    0.57
     newOwner
    0.56
    ViewFeatures
    0.54
    Activations Density 14.433%

    No Known Activations