© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11911
    Prev
    Next
    INDEX
    Explanations

    mentions of a method or approach with some qualifiers, often in technical documents

    oai_token-act-pair · gemini-2.0-flash

    considerations or options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    smithy
    -0.54
     sauvages
    -0.49
     blanches
    -0.48
    expandindo
    -0.48
     poveznice
    -0.46
     tecnici
    -0.43
     piele
    -0.42
     egentlig
    -0.41
    Referenties
    -0.41
     referencias
    -0.41
    POSITIVE LOGITS
    ]));
    0.63
    ScopeManager
    0.61
    itoneal
    0.59
     resourceCulture
    0.57
    rifugal
    0.57
    jspx
    0.57
    andExpect
    0.56
    "])
    0.56
    τέλε
    0.56
     alternate
    0.55
    Activations Density 0.449%

    No Known Activations