© 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. 8258
    Prev
    Next
    INDEX
    Explanations

    words suggesting subjectivity or opinion.

    oai_token-act-pair · gemini-2.0-flash

    abstract concepts

    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
    úsqueda
    -0.56
    ]]=
    -0.53
    nativeElement
    -0.53
    SOUNDBITE
    -0.53
    rrggbb
    -0.52
    出版年
    -0.51
    ])]
    -0.51
    طلحات
    -0.50
     Италијани
    -0.49
    nesium
    -0.49
    POSITIVE LOGITS
     onOptions
    0.57
     doInBackground
    0.55
     AttributeSet
    0.54
    TagMode
    0.52
    EndInit
    0.52
     InputDecoration
    0.50
     EconPapers
    0.50
     IBOutlet
    0.49
     كومونز
    0.48
     Meksiku
    0.47
    Activations Density 0.689%

    No Known Activations