© 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. 7479
    Prev
    Next
    INDEX
    Explanations

    words or phrases that commonly appear in technical documentation, especially relating to computer architecture, signal processing, or scientific experiments.

    oai_token-act-pair · gemini-2.0-flash

    threshold/cutoff values

    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
    Datuak
    -0.98
     threshold
    -0.84
    threshold
    -0.77
     thresholds
    -0.77
     Threshold
    -0.76
    Threshold
    -0.68
    rungsseite
    -0.68
     الاطلاع
    -0.66
    帖最后由
    -0.65
    map
    -0.63
    POSITIVE LOGITS
    Pitch
    0.46
     Pitch
    0.46
    Salva
    0.44
    zesi
    0.43
     hust
    0.43
    getDrawable
    0.42
    raborty
    0.42
     slo
    0.42
     tragedia
    0.42
    Enroll
    0.41
    Activations Density 11.881%

    No Known Activations