© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6324
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and characters used in references and codes

    oai_token-act-pair · gemini-2.0-flash

    technical and scientific texts

    np_max-act-logits · gemini-2.0-flash

    say "single-character"

    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
    1
    -2.00
    2
    -1.96
    3
    -1.88
    5
    -1.83
    6
    -1.79
    4
    -1.78
    7
    -1.76
    9
    -1.72
    8
    -1.70
    0
    -1.64
    POSITIVE LOGITS
     CanadaChoose
    0.54
     nahilalakip
    0.53
     مواليد
    0.51
     ब्रेकडाउन
    0.51
    PropertyChanging
    0.51
    ientôt
    0.51
    Amicalement
    0.50
     للاسماء
    0.50
    bkz
    0.49
    iveau
    0.48
    Activations Density 22.473%

    No Known Activations