© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 478
    Prev
    Next
    INDEX
    Explanations

    code snippets including programming keywords

    oai_token-act-pair · gemini-2.0-flash

    Code and database context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ofition
    -0.53
    Contours
    -0.48
    gesteld
    -0.48
    Interface
    -0.45
    Options
    -0.45
    Bundle
    -0.45
    Platforms
    -0.45
    Configuration
    -0.45
    nefs
    -0.44
     hő
    -0.44
    POSITIVE LOGITS
    Geplaatst
    0.69
     "..\..\..\
    0.61
     Audiodateien
    0.59
     bezeichneter
    0.56
    MemberId
    0.55
     LoginComponent
    0.55
     Савезне
    0.54
     RIAA
    0.54
     Sacrament
    0.54
    FromNib
    0.54
    Activations Density 4.111%

    No Known Activations