© 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. 6344
    Prev
    Next
    INDEX
    Explanations

    the letters "l, r, m, d" that are not followed by a space (i.e., inside words)

    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
    n
    -1.11
    t
    -1.10
    m
    -0.96
    d
    -0.95
    c
    -0.94
    b
    -0.94
    l
    -0.91
    g
    -0.90
    p
    -0.90
    s
    -0.89
    POSITIVE LOGITS
    ítő
    0.35
    Історія
    0.35
    posito
    0.34
    ämmer
    0.34
    ümüş
    0.34
    Особенности
    0.34
    ükemmel
    0.34
    OMBIA
    0.33
    ่วม
    0.33
    ellingham
    0.33
    Activations Density 3.171%

    No Known Activations