© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10815
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to interpersonal relationships, a mix of question-answer pairs about web pages in what seems to be Russian and words related to meals.

    oai_token-act-pair · gemini-2.0-flash

    your

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     you
    -2.27
    you
    -1.71
    You
    -1.48
     You
    -1.40
     thee
    -1.38
     YOU
    -1.32
     vous
    -1.28
    YOU
    -1.27
     você
    -1.20
     вам
    -1.20
    POSITIVE LOGITS
     your
    0.64
     tuo
    0.58
     tua
    0.55
    Your
    0.48
    your
    0.47
     Ihr
    0.45
    tuo
    0.44
     yourself
    0.43
    lerin
    0.43
     du
    0.43
    Activations Density 2.634%

    No Known Activations