© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10545
    Prev
    Next
    INDEX
    Explanations

    reports of conversations, potentially with some focus on formal or legal settings

    oai_token-act-pair · gemini-2.0-flash

    Talking/exchanging information

    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
     parut
    -0.52
    pendidikan
    -0.52
    ه‌اند
    -0.50
     shogun
    -0.50
    EndInit
    -0.50
     skolen
    -0.49
    tagHelperRunner
    -0.49
    BrowserModule
    -0.49
     élastique
    -0.49
    GEBURTS
    -0.49
    POSITIVE LOGITS
     $
    0.58
    awaiter
    0.57
    ControllerAdvice
    0.57
     _$
    0.55
     disponibilités
    0.52
     onResponse
    0.52
    zzleHttp
    0.52
    ftc
    0.51
    ::_
    0.51
    ::$
    0.50
    Activations Density 30.652%

    No Known Activations