© 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. 7064
    Prev
    Next
    INDEX
    Explanations

    text focused on personal opinions or anecdotes regarding social or political issues.

    oai_token-act-pair · gemini-2.0-flash

    sociological commentary

    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
     externi
    -0.53
     Mesmo
    -0.40
     légales
    -0.40
     niebieski
    -0.35
     sanitaire
    -0.35
     Unexpected
    -0.34
     niebies
    -0.33
    andten
    -0.33
     censi
    -0.33
    A
    -0.33
    POSITIVE LOGITS
    GOTREF
    0.98
    DockStyle
    0.88
    ChildScrollView
    0.84
    ReusableCell
    0.84
    AnchorStyles
    0.81
    Geplaatst
    0.80
    पया
    0.79
     BoxFit
    0.78
    __(/*!
    0.78
    出版年
    0.77
    Activations Density 10.045%

    No Known Activations