© 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. 12462
    Prev
    Next
    INDEX
    Explanations

    code and code-like syntax

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     PPS
    -0.97
     PB
    -0.90
     PPA
    -0.89
     PPD
    -0.88
     PMP
    -0.88
     PCC
    -0.87
     PQ
    -0.86
     PSP
    -0.86
     Pm
    -0.84
     PW
    -0.83
    POSITIVE LOGITS
    AndroidJUnit
    0.55
     CreateTagHelper
    0.45
    oolean
    0.45
    RegistryLite
    0.43
    godic
    0.42
     Roskov
    0.42
    󠁴
    0.42
    lamydia
    0.41
    держа
    0.41
     Den
    0.40
    Activations Density 3.613%

    No Known Activations