© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12410
    Prev
    Next
    INDEX
    Explanations

    phrases related to questions and answers in a multiple-choice format, with an emphasis on tagging correct and incorrect answer choices

    oai_token-act-pair · gemini-2.0-flash

    Questions and Answers with parsing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     deutscher
    -0.86
     neuen
    -0.86
     kleinen
    -0.77
     öffentlichen
    -0.75
     weiteren
    -0.75
     gesamten
    -0.75
     deutschen
    -0.74
     privaten
    -0.73
     zweiten
    -0.73
     englischen
    -0.73
    POSITIVE LOGITS
     BoxFit
    0.63
    IBAction
    0.53
     ''}
    0.52
    σιμοποι
    0.52
    Insee
    0.49
    ++];
    0.47
    PYX
    0.47
     DBNull
    0.47
    <?
    0.46
    ípios
    0.46
    Activations Density 0.308%

    No Known Activations