© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10038
    Prev
    Next
    INDEX
    Explanations

    terms related to the concepts of politics, public communication, and breaking the law

    oai_token-act-pair · gemini-2.0-flash

    public relations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    DoubleQuotes
    -0.67
    ędzy
    -0.60
     typename
    -0.59
     voudrais
    -0.57
    usnya
    -0.57
    “…”
    -0.56
    __);
    -0.56
     viewType
    -0.55
     adanya
    -0.54
    hlander
    -0.54
    POSITIVE LOGITS
     nakalista
    0.76
     BoxDecoration
    0.68
    Hozzáférés
    0.61
    الإنجليزية
    0.56
    igshid
    0.53
    ukone
    0.53
    erdere
    0.51
     __
    0.51
    ffl
    0.49
    AnchorStyles
    0.49
    Activations Density 0.276%

    No Known Activations