© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15315
    Prev
    Next
    INDEX
    Explanations

    movie reviews that give a film a rating

    oai_token-act-pair · gemini-2.0-flash

    words related to programming or code

    np_token-act-pair-logits · gpt-4o-mini

    programming/foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     tartalomajánló
    -0.81
     Waray
    -0.60
     RSSSF
    -0.58
     <<<<<<<<<<<<<<
    -0.56
     floss
    -0.55
     Chanti
    -0.53
     pleaſure
    -0.52
     moulin
    -0.52
     Cushman
    -0.50
     Kochen
    -0.50
    POSITIVE LOGITS
    InjectAttribute
    0.60
     ComVisible
    0.58
    GenerationType
    0.53
    ruptedException
    0.52
     تعدى
    0.51
     vendus
    0.49
     IndexError
    0.49
    日的
    0.48
    脚注の使い方
    0.46
    зах
    0.46
    Activations Density 2.076%

    No Known Activations