© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1093
    Prev
    Next
    INDEX
    Explanations

    code and software licenses, as well as information about reporting bugs.

    oai_token-act-pair · gemini-2.0-flash

    code and file snippets

    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
     يتيمه
    -0.64
    SocketAddress
    -0.64
    cdnjs
    -0.62
    igshid
    -0.57
    sdl
    -0.56
     che
    -0.54
    rxjs
    -0.54
     tư
    -0.53
    NavController
    -0.52
    netinet
    -0.52
    POSITIVE LOGITS
    ++
    
    1.27
    )++;
    1.18
    )");
    
    1.17
    )";
    
    1.16
     itſelf
    1.14
    "])
    
    1.13
    !")
    
    1.11
    "]);
    
    1.11
     Efq
    1.07
    })*/
    1.06
    Activations Density 40.555%

    No Known Activations