© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13509
    Prev
    Next
    INDEX
    Explanations

    mentions of racially charged incidents and opinions regarding race.

    oai_token-act-pair · gemini-2.0-flash

    Legal cases and crime

    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
    zzlies
    -0.80
    IsContent
    -0.79
     transférez
    -0.77
     vPvB
    -0.73
    OGND
    -0.73
    icordia
    -0.71
     useDispatch
    -0.68
    RenderAtEndOf
    -0.67
    LLocation
    -0.66
    andExpect
    -0.66
    POSITIVE LOGITS
     security
    0.40
    Cré
    0.40
     giuri
    0.39
    tagHelperRunner
    0.38
    security
    0.37
     کر
    0.35
     interrump
    0.35
    気付
    0.35
     güven
    0.34
    ====
    0.33
    Activations Density 1.520%

    No Known Activations