© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3462
    Prev
    Next
    INDEX
    Explanations

    phrases about treating oneself.

    oai_token-act-pair · gemini-2.0-flash

    treat yourself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    MethodManager
    -0.58
     OSError
    -0.52
    ंदीखरीदारी
    -0.52
     porcelaine
    -0.52
     paroi
    -0.52
    Hochspringen
    -0.52
     céramique
    -0.51
     sagesse
    -0.51
     jugement
    -0.50
    WarningLevel
    -0.50
    POSITIVE LOGITS
    ]));
    0.67
     CURIAM
    0.66
    identa
    0.62
    oppa
    0.59
    ])));
    0.59
    __))
    0.58
    webElementGuid
    0.58
    ()]
    0.57
    клопе
    0.57
    ]>=
    0.56
    Activations Density 2.141%

    No Known Activations