© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10083
    Prev
    Next
    INDEX
    Explanations

    code blocks, particularly the beginnings and ends of functions and conditional statements in languages such as Go

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    didSet
    -0.55
    Gemeinden
    -0.52
    adell
    -0.50
    itta
    -0.48
    initWith
    -0.48
    unittest
    -0.47
     Mon
    -0.45
    OPHER
    -0.45
    śli
    -0.44
    VersionUID
    -0.44
    POSITIVE LOGITS
    ftagPool
    0.64
     saites
    0.63
    styleUrls
    0.59
    fillType
    0.58
    LabelTagHelper
    0.56
    InputBorder
    0.53
    </tfoot>
    0.53
     liberi
    0.52
     cherchés
    0.52
     HasFactory
    0.49
    Activations Density 0.639%

    No Known Activations