© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4463
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "political", "Clinton", or other related concepts.

    oai_token-act-pair · gemini-2.0-flash

    political

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    SourceChecksum
    -0.67
    évaluateur
    -0.65
     Meksiku
    -0.64
    StoryboardSegue
    -0.63
     Besoin
    -0.57
    Vidite
    -0.57
     disambiguazione
    -0.57
    AndroidJUnit
    -0.57
     CWE
    -0.56
     nahilalakip
    -0.54
    POSITIVE LOGITS
    PRWEB
    0.51
    InitStruct
    0.45
    الإنجليزية
    0.45
     naik
    0.45
     str
    0.43
    att
    0.42
    rrggbb
    0.42
    addColumn
    0.42
    adə
    0.41
    neurial
    0.41
    Activations Density 2.320%

    No Known Activations