© 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. 11116
    Prev
    Next
    INDEX
    Explanations

    commas and periods close together, often followed by numbers or single letters

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    Clik
    -0.62
     المعيارى
    -0.52
     sær
    -0.52
     šķ
    -0.51
    setcounter
    -0.49
     fraî
    -0.47
    airro
    -0.47
    ...
    -0.47
     säll
    -0.47
     själ
    -0.47
    POSITIVE LOGITS
    "}";
    0.71
    ]),
    0.69
    Дереккөздер
    0.67
     >=",
    0.65
    $")
    0.64
    ⓧ
    0.63
    ]]);
    0.63
    /}.
    0.63
     */,
    0.62
    OSIS
    0.62
    Activations Density 1.316%

    No Known Activations