© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2870
    Prev
    Next
    INDEX
    Explanations

    product reviews with scores

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     grade
    -1.27
     grades
    -1.20
     score
    -1.15
     Grade
    -1.15
    Grade
    -1.09
     scores
    -1.06
    grade
    -1.03
     GRADE
    -1.00
    score
    -0.98
     Score
    -0.97
    POSITIVE LOGITS
     Chwiliwch
    0.59
     المعيارى
    0.55
    LookAnd
    0.52
    BrowserModule
    0.52
     miniatur
    0.51
    ändigkeit
    0.50
    kesha
    0.50
     PopupWindow
    0.49
     ISNI
    0.49
    出版年
    0.49
    Activations Density 0.617%

    No Known Activations