© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6420
    Prev
    Next
    INDEX
    Explanations

    C++ code related to iostreams and user input

    oai_token-act-pair · gemini-2.0-flash

    cout

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    delete
    -0.99
     delete
    -0.81
     freeing
    -0.77
    free
    -0.77
     liberated
    -0.75
     free
    -0.72
     freed
    -0.69
     frees
    -0.69
     Garbage
    -0.69
    Free
    -0.68
    POSITIVE LOGITS
    addCriterion
    0.44
    Manfaat
    0.43
    LookAnd
    0.42
    canto
    0.42
     Moran
    0.42
     Oll
    0.41
    polis
    0.41
    ıza
    0.41
     fil
    0.41
     weit
    0.40
    Activations Density 1.148%

    No Known Activations