© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10355
    Prev
    Next
    INDEX
    Explanations

    words related to medicine/drugs and comparisons/equivalents

    oai_token-act-pair · gemini-2.0-flash

    like or equivalent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    tvguidetime
    -0.79
    addPreferredGap
    -0.73
     كومونز
    -0.67
    complexContent
    -0.63
    ագրություններ
    -0.60
    Personendaten
    -0.60
    Gön
    -0.59
     Lightboxes
    -0.59
    )_/¯
    -0.59
    PreExecute
    -0.58
    POSITIVE LOGITS
     equivalent
    0.60
     équi
    0.59
     equivalente
    0.53
     substitute
    0.53
     Equivalent
    0.52
    ɚ
    0.51
    Equivalent
    0.51
    impl
    0.49
     equival
    0.48
     analogues
    0.48
    Activations Density 0.953%

    No Known Activations