© 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. 13130
    Prev
    Next
    INDEX
    Explanations

    mentions of apps or email programs

    oai_token-act-pair · gemini-2.0-flash

    Apps and software descriptions

    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
    saraba
    -0.59
    SPJ
    -0.54
    esgue
    -0.51
     protecting
    -0.50
    CLC
    -0.50
     assisting
    -0.49
    RegistryLite
    -0.49
    KEYCODE
    -0.49
     relieving
    -0.48
    αλ
    -0.46
    POSITIVE LOGITS
    NewUrlParser
    0.64
     OnInit
    0.59
    providedIn
    0.58
     mourut
    0.57
    XmlAccessType
    0.54
    WritableDatabase
    0.52
     greateſt
    0.51
     getArguments
    0.51
     viewType
    0.51
     StatefulWidget
    0.48
    Activations Density 3.555%

    No Known Activations