© 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. 6452
    Prev
    Next
    INDEX
    Explanations

    positive and negative sentiment words and phrases

    oai_token-act-pair · gemini-2.0-flash

    expressing sentiment

    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
    R
    -0.44
     catch
    -0.42
    vb
    -0.40
    flat
    -0.40
    vnd
    -0.39
    mo
    -0.38
     R
    -0.38
    owie
    -0.38
     cuello
    -0.38
     Mid
    -0.37
    POSITIVE LOGITS
     فريبيس
    1.09
    ThroughAttribute
    1.04
    contentLoaded
    0.96
    ⓧ
    0.94
    tagHelperRunner
    0.94
    WithIOException
    0.84
    msgTypes
    0.84
     AssemblyCompany
    0.84
    expandindo
    0.84
     propOrder
    0.84
    Activations Density 3.257%

    No Known Activations