© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12748
    Prev
    Next
    INDEX
    Explanations

    instances of "you" along with time-sensitive words like "ended," "finished" and references to payment plans or financial tools.

    oai_token-act-pair · gemini-2.0-flash

    has/have

    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
     كومونز
    -0.89
     EconPapers
    -0.79
     Вікі
    -0.69
    +#+#
    -0.68
    Décès
    -0.68
     <<<<<<<<<<<<<<
    -0.67
    thâu
    -0.66
    tonsoft
    -0.66
    Tikang
    -0.66
    Datuak
    -0.66
    POSITIVE LOGITS
     has
    1.41
     have
    1.19
    Has
    1.17
     Has
    1.13
    has
    1.03
     Have
    0.96
    Have
    0.89
     hasn
    0.87
     heeft
    0.87
     telah
    0.87
    Activations Density 2.577%

    No Known Activations