© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3993
    Prev
    Next
    INDEX
    Explanations

    mentions of rewrites, especially in the context of code or policy

    oai_token-act-pair · gemini-2.0-flash

    Re-doing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Chwiliwch
    -0.68
    AddTagHelper
    -0.66
     HttpNotFound
    -0.63
     DBNull
    -0.61
     فريبيس
    -0.59
     שוליים
    -0.58
    jsonwebtoken
    -0.57
     חיצוניים
    -0.57
    GrantedAuthority
    -0.56
    Autoritní
    -0.54
    POSITIVE LOGITS
     re
    1.51
     reform
    1.43
     redesign
    1.41
     overhaul
    1.39
     revamp
    1.38
     remodel
    1.24
     rewrite
    1.24
     remake
    1.23
     rebuild
    1.23
     rework
    1.23
    Activations Density 1.050%

    No Known Activations