© 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. 4014
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are considered indecent or offensive.

    oai_token-act-pair · gemini-2.0-flash

    dirt

    np_max-act · gemini-2.0-flash

    dirt

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ing
    -1.03
     ainfi
    -0.87
    BASEPATH
    -0.83
    WebServlet
    -0.83
    ING
    -0.82
     Millar
    -0.82
    providedIn
    -0.81
     circonst
    -0.80
     indépendant
    -0.78
     survie
    -0.78
    POSITIVE LOGITS
    ?")
    0.72
    =-=-=-=-
    0.69
    ).]
    0.65
    ^*)
    0.65
    ).
    0.64
     *>
    0.64
    }'.
    0.63
    *]
    0.62
    》。
    0.61
    ].)
    0.60
    Activations Density 2.405%

    No Known Activations