© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11938
    Prev
    Next
    INDEX
    Explanations

    code that resembles loops with "i" and "j" iterators, often initialized or compared to 0 or 1

    oai_token-act-pair · gemini-2.0-flash

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    till
    -0.54
    }\|
    -0.52
    }]
    -0.50
    }`).
    -0.50
    }],
    -0.49
     until
    -0.48
    }$}
    -0.47
     untill
    -0.47
    ]=-
    -0.47
    bigskip
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    0.67
    AccessorTable
    0.65
    новниш
    0.63
    complexContent
    0.61
    dataclass
    0.60
    OGND
    0.60
    úgó
    0.60
    Enllaces
    0.59
    SPATH
    0.58
    Obrázky
    0.58
    Activations Density 0.506%

    No Known Activations