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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7855
    Prev
    Next
    INDEX
    Explanations

    conversational content, especially responses in a question and answering context

    oai_token-act-pair · gemini-2.0-flash

    Software technologies

    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
     colesterol
    -0.41
    itonitis
    -0.40
     bruises
    -0.38
     WIFE
    -0.36
    nur
    -0.36
     GIRLS
    -0.35
     baptism
    -0.35
    rumah
    -0.35
     palsy
    -0.34
    สึก
    -0.34
    POSITIVE LOGITS
     Gartner
    0.74
     Magento
    0.68
     ERP
    0.67
     ArcGIS
    0.66
     VPN
    0.66
     SharePoint
    0.65
     GIS
    0.65
     FPGA
    0.65
     Dropbox
    0.64
     Google
    0.64
    Activations Density 37.614%

    No Known Activations