© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15200
    Prev
    Next
    INDEX
    Explanations

    code related to software development, specifically Java and Android

    oai_token-act-pair · gemini-2.0-flash

    Non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     onCreateView
    -0.61
    wag
    -0.53
    pan
    -0.48
    3
    -0.45
    PropertyChanged
    -0.44
    TagHelper
    -0.44
    5
    -0.44
    istoitu
    -0.43
    va
    -0.43
     Pan
    -0.43
    POSITIVE LOGITS
    PositiveButton
    0.75
    ագրություններ
    0.73
    ThroughAttribute
    0.71
     poffe
    0.61
     resourceCulture
    0.60
    complexContent
    0.59
     صوتيه
    0.59
    例句
    0.58
    Източници
    0.58
    Референце
    0.58
    Activations Density 0.060%

    No Known Activations