© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6658
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related discussions in multiple languages.

    oai_token-act-pair · gemini-2.0-flash

    programming code and errors

    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
     Theſe
    -0.63
     GoogleFonts
    -0.55
     TAMBÉM
    -0.54
     Bucure
    -0.50
    vailable
    -0.49
    Vorteile
    -0.48
     Efq
    -0.48
     humanas
    -0.48
     Monfieur
    -0.47
     himſelf
    -0.47
    POSITIVE LOGITS
     her
    1.20
    her
    0.82
     الحره
    0.69
    Her
    0.69
     متعلقه
    0.66
     Her
    0.63
    gameserver
    0.60
    badlogic
    0.55
    بوابة
    0.53
    portál
    0.53
    Activations Density 1.191%

    No Known Activations