© 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. 1013
    Prev
    Next
    INDEX
    Explanations

    mentions of designed or invented products.

    oai_token-act-pair · gemini-2.0-flash

    Objects and items

    np_max-act-logits · gemini-2.0-flash

    products Method used: 1 — because top tokens are item names — products

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Personendaten
    -0.57
     Dawes
    -0.49
     Eing
    -0.47
     Дата
    -0.47
    Portail
    -0.47
    ENSIS
    -0.45
     comment
    -0.44
    annotation
    -0.43
    tieg
    -0.43
    LogEntry
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.57
    //
    0.57
     snippetHide
    0.57
    APORE
    0.57
     InputDecoration
    0.56
     mergeFrom
    0.56
    DockStyle
    0.56
    WidgetItem
    0.54
    netinet
    0.53
    richTextPanel
    0.52
    Activations Density 6.283%

    No Known Activations