© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13148
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics, law, or cultural bans.

    oai_token-act-pair · gemini-2.0-flash

    legal/political articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     iprot
    -0.59
    ništvo
    -0.46
    flink
    -0.45
     flexível
    -0.45
     esegu
    -0.44
     arvio
    -0.44
    yargs
    -0.44
     collaborateurs
    -0.44
     the
    -0.43
    fjspx
    -0.43
    POSITIVE LOGITS
    Portály
    0.82
    Portale
    0.77
     المعيارى
    0.68
    脚注の使い方
    0.68
    älv
    0.66
    ########.
    0.66
    ranath
    0.65
    expandindo
    0.63
    hône
    0.60
    <%=
    0.60
    Activations Density 4.797%

    No Known Activations