© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    common contractions and numbers or codes with delimiters

    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
    Injectable
    -0.48
     становника
    -0.44
     للاسماء
    -0.42
     négoci
    -0.41
    seiti
    -0.39
    igshid
    -0.38
     consultato
    -0.37
    )()
    -0.37
    flasche
    -0.36
     Unfortunately
    -0.35
    POSITIVE LOGITS
     EconPapers
    0.86
     nahilalakip
    0.75
     SafeMath
    0.72
    ########.
    0.71
     noDo
    0.64
     cielos
    0.62
    addCriterion
    0.62
    /******/
    0.62
    yntaxException
    0.62
    #+#
    0.61
    Activations Density 21.276%

    No Known Activations