© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13734
    Prev
    Next
    INDEX
    Explanations

    code snippets including variable assignments, array indexing, and bitwise operations.

    oai_token-act-pair · gemini-2.0-flash

    say right parentheses/brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    nloa
    -0.69
    FieldDescriptor
    -0.67
    AutoScale
    -0.65
    avyzd
    -0.65
    Aiheesta
    -0.63
    GRANTED
    -0.63
    Collegamenti
    -0.62
    ValueGeneration
    -0.61
    ipts
    -0.60
    IsContent
    -0.59
    POSITIVE LOGITS
    ReusableCell
    0.51
     zijne
    0.51
     oorlog
    0.46
     étrangères
    0.46
     referenties
    0.46
     normaux
    0.45
     originaux
    0.44
     russes
    0.44
     prestazioni
    0.44
     présidenti
    0.42
    Activations Density 3.020%

    No Known Activations