© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2044
    Prev
    Next
    INDEX
    Explanations

    words that are being used in an opinion, potentially based on negative connotation

    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_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
    ftagPool
    -0.68
    Whilst
    -0.60
     Whilst
    -0.57
     whilst
    -0.54
     Firstly
    -0.52
    offsetof
    -0.49
    BagConstraints
    -0.49
    Firstly
    -0.48
     uintptr
    -0.48
    brilliant
    -0.47
    POSITIVE LOGITS
     Wiktionnaire
    0.71
     المعيارى
    0.63
     oprot
    0.62
     surla
    0.61
     كومونز
    0.57
     geldig
    0.56
    énario
    0.56
    expandindo
    0.55
     ProtoMessage
    0.54
    openConnection
    0.53
    Activations Density 7.715%

    No Known Activations