© 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. 3953
    Prev
    Next
    INDEX
    Explanations

    european diacritic letters and fragments of Hungarian place names

    oai_token-act-pair · gemini-2.0-flash

    Foreign language/Technical text

    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
    áját
    -0.69
     entanto
    -0.69
    calipsis
    -0.64
    hingga
    -0.59
    sequently
    -0.59
    TagHelper
    -0.59
    ごちそうさまでした
    -0.59
    ḻ
    -0.58
    yaszt
    -0.58
    šanai
    -0.57
    POSITIVE LOGITS
    ínű
    0.90
    ]]
    0.74
    ngdoc
    0.69
    :])
    0.68
    ]))
    0.68
    KommentareTeilen
    0.66
    )\,
    0.65
    //
    0.64
     ]
    0.63
    }]
    0.62
    Activations Density 0.117%

    No Known Activations