© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11248
    Prev
    Next
    INDEX
    Explanations

    the user "Chex" in a chat log

    oai_token-act-pair · gemini-2.0-flash

    Che

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Che
    -2.66
    Che
    -2.64
    che
    -2.52
     che
    -2.36
    CHE
    -2.13
     CHE
    -2.11
     cheating
    -1.26
     chemo
    -1.23
     cheat
    -1.13
    ché
    -1.11
    POSITIVE LOGITS
     Púb
    0.62
    HtmlAttribute
    0.58
     MotionEvent
    0.57
     Akismet
    0.56
    HSSF
    0.55
     ChromeDriver
    0.53
    onViewCreated
    0.52
    Abend
    0.51
     réfugi
    0.51
    CppCodeGen
    0.51
    Activations Density 0.430%

    No Known Activations