© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12782
    Prev
    Next
    INDEX
    Explanations

    instances of personal opinions or statements

    oai_token-act-pair · gemini-2.0-flash

    blog post context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     stuff
    -1.48
     crap
    -1.30
     STUFF
    -1.30
     Stuff
    -1.25
    stuff
    -1.23
    Stuff
    -1.20
     dude
    -1.14
     dudes
    -1.13
     thingy
    -1.12
     shit
    -1.10
    POSITIVE LOGITS
     مشين
    0.67
    ướ
    0.56
    principalTable
    0.53
    setViewportView
    0.52
    enumi
    0.51
    ="/">
    0.50
    Geplaatst
    0.50
     kív
    0.49
    })*/
    0.49
    ubility
    0.49
    Activations Density 3.433%

    No Known Activations