© 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. 9361
    Prev
    Next
    INDEX
    Explanations

    bulleted lists and uses of the word "wouldn't" or "weren't"

    oai_token-act-pair · gemini-2.0-flash

    Technical documentation

    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
    NUMX
    -0.88
     Efq
    -0.64
     doubtnut
    -0.57
    ſelves
    -0.56
    ^(@)
    -0.55
     myſelf
    -0.50
    ".
    -0.47
    ſelf
    -0.47
     leaſt
    -0.47
    ."*
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.66
    Geplaatst
    0.65
     recevrez
    0.64
    ⓧ
    0.62
    Tell
    0.59
     graines
    0.59
     fumée
    0.59
     continúas
    0.58
     dég
    0.58
     kasarigan
    0.57
    Activations Density 7.837%

    No Known Activations