© 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. 4804
    Prev
    Next
    INDEX
    Explanations

    seemingly random alphanumeric sequences and characters within a code-like or data structure environment.

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     propOrder
    -0.44
     censiti
    -0.43
     Manchuria
    -0.37
    AddTagHelper
    -0.36
    يكب
    -0.35
    toMatchSnapshot
    -0.35
    ьаж
    -0.35
    ES
    -0.35
    TintMode
    -0.35
     endwhile
    -0.35
    POSITIVE LOGITS
    n
    1.55
    d
    1.47
    t
    1.45
    p
    1.45
    m
    1.41
    l
    1.39
    c
    1.38
    b
    1.34
    r
    1.29
    f
    1.29
    Activations Density 2.428%

    No Known Activations