© 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. 5385
    Prev
    Next
    INDEX
    Explanations

    mentions of things that are secret or hidden.

    oai_token-act-pair · gemini-2.0-flash

    Secrets

    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
     secret
    -2.83
     Secret
    -2.41
    secret
    -2.38
    Secret
    -2.30
     SECRET
    -2.14
     secreto
    -2.00
    SECRET
    -1.79
     segreto
    -1.72
     секре
    -1.65
    秘密
    -1.58
    POSITIVE LOGITS
    positivos
    0.53
    SpringRunner
    0.48
     Foss
    0.47
     Référence
    0.47
     vlak
    0.46
    mc
    0.46
     препратки
    0.46
     javafx
    0.44
    mage
    0.43
     eligibility
    0.43
    Activations Density 2.725%

    No Known Activations