© 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. 7557
    Prev
    Next
    INDEX
    Explanations

    code-related terms and sections of math and logic problems, especially those involving probability

    oai_token-act-pair · gemini-2.0-flash

    C code structs

    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
     sp
    -0.68
     sw
    -0.66
     sc
    -0.66
     sa
    -0.65
     sm
    -0.65
     s
    -0.63
     sy
    -0.63
     sl
    -0.63
     sg
    -0.62
     sk
    -0.60
    POSITIVE LOGITS
    ScreenState
    0.49
    loài
    0.48
     חיצוניים
    0.48
     Spell
    0.47
     médec
    0.47
     charité
    0.47
     pauv
    0.47
     réfrig
    0.45
     feroit
    0.45
     vectoriales
    0.44
    Activations Density 16.472%

    No Known Activations