© 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. 5357
    Prev
    Next
    INDEX
    Explanations

    negative words co-occuring with words related to medical conditions

    oai_token-act-pair · gemini-2.0-flash

    Hyphens/dashes

    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
     doInBackground
    -0.92
    tagext
    -0.90
    mobileqq
    -0.90
    ^(@)
    -0.90
    🏻‍♀️
    -0.90
     propOrder
    -0.89
     Monfieur
    -0.87
    NUMX
    -0.85
     Efq
    -0.85
    tvguidetime
    -0.83
    POSITIVE LOGITS
    -
    1.99
    ‑
    1.08
    ‐
    0.92
    -\
    0.88
    -(
    0.81
    $-
    0.80
    −
    0.79
    -,
    0.79
    –
    0.79
    ®-
    0.71
    Activations Density 2.407%

    No Known Activations