© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8110
    Prev
    Next
    INDEX
    Explanations

    words associated with forming a conclusion or making a judgement

    oai_token-act-pair · gemini-2.0-flash

    certainty predictions possibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Monfieur
    -1.10
     myſelf
    -1.07
     itſelf
    -1.04
     Jefus
    -0.99
     himſelf
    -0.97
     Majefty
    -0.91
     themſelves
    -0.89
     poffe
    -0.89
     neceff
    -0.87
     Shakspeare
    -0.87
    POSITIVE LOGITS
     mà
    0.48
    utnik
    0.48
    urst
    0.48
    enumi
    0.47
    StringTokenizer
    0.44
     Str
    0.43
     pr
    0.42
     di
    0.40
     dan
    0.40
     fa
    0.40
    Activations Density 1.531%

    No Known Activations