© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13975
    Prev
    Next
    INDEX
    Explanations

    phrases involving political controversies and government actions

    oai_token-act-pair · gemini-2.0-flash

    social/political issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ónicas
    -0.48
    RenderAtEndOf
    -0.48
    Latch
    -0.48
    ITOS
    -0.45
    AGGIO
    -0.44
    GERY
    -0.44
    lcm
    -0.44
    enderror
    -0.44
    न्म
    -0.43
    fiore
    -0.43
    POSITIVE LOGITS
     AssemblyCompany
    0.72
     FetchType
    0.71
    Personensuche
    0.71
     insuffisamment
    0.70
    omitempty
    0.63
    homonymie
    0.60
    httphttps
    0.60
    principalColumn
    0.59
     invokingState
    0.58
     AssemblyCulture
    0.57
    Activations Density 3.551%

    No Known Activations