© 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. 11714
    Prev
    Next
    INDEX
    Explanations

    opinions and beliefs.

    oai_token-act-pair · gemini-2.0-flash

    injustice

    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
    افظة
    -0.61
    RectangleBorder
    -0.60
    IBOutlet
    -0.55
    Попис
    -0.55
    NUMX
    -0.55
    Bronnen
    -0.54
     onPostExecute
    -0.54
    ":[{
    -0.52
    НИК
    -0.52
     AssemblyVersion
    -0.50
    POSITIVE LOGITS
     Fior
    0.53
    ưu
    0.52
    tanleria
    0.49
    govina
    0.49
    AISSEE
    0.47
     चीज़ों
    0.46
    moveToFirst
    0.46
    خصة
    0.46
    Isolated
    0.45
     isolation
    0.45
    Activations Density 1.030%

    No Known Activations