© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6692
    Prev
    Next
    INDEX
    Explanations

    words expressing negative sentiment or bad qualities

    oai_token-act-pair · gemini-2.0-flash

    bad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Mundi
    -0.80
    MemoryWarning
    -0.74
    ValueStyle
    -0.70
    NewUrlParser
    -0.68
    awtextra
    -0.67
    contentLoaded
    -0.66
    Hướng
    -0.65
    ContentLoaded
    -0.65
    Portail
    -0.63
    دانشنامهٔ
    -0.63
    POSITIVE LOGITS
    +#+#
    0.57
    rep
    0.47
    fel
    0.43
    WidgetItem
    0.41
    rap
    0.41
    mios
    0.40
     razão
    0.40
    ni
    0.40
    rem
    0.39
    seeds
    0.39
    Activations Density 6.676%

    No Known Activations