© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11612
    Prev
    Next
    INDEX
    Explanations

    mentions of challenging or problematic subjects

    oai_token-act-pair · gemini-2.0-flash

    topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     subject
    -0.93
     topic
    -0.90
     topics
    -0.87
     subjects
    -0.86
     matter
    -0.79
    subject
    -0.77
     issue
    -0.74
     Topic
    -0.73
    Subject
    -0.72
    TOPIC
    -0.72
    POSITIVE LOGITS
     дописавши
    0.88
    脚注の使い方
    0.82
    oa̍t
    0.73
     vectorielles
    0.72
     فريبيس
    0.68
     صوتيه
    0.66
    msgTypes
    0.65
    TargetException
    0.64
    MethodManager
    0.64
     Besøkt
    0.63
    Activations Density 17.453%

    No Known Activations