© 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. 14951
    Prev
    Next
    INDEX
    Explanations

    code snippets including variable declarations, type specifications, and control flow statements (if, for), and function calls

    oai_token-act-pair · gemini-2.0-flash

    variable names

    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
     Infórmanos
    -0.79
    ########.
    -0.61
    
    -0.59
    }}_{\
    -0.57
    )":
    -0.54
    }),
    -0.54
     AssemblyCulture
    -0.53
    qü
    -0.52
    }}_
    -0.52
     Permanent
    -0.52
    POSITIVE LOGITS
     newVal
    0.63
     currentNode
    0.53
     bookId
    0.53
     newName
    0.51
    ujudkan
    0.51
     eventName
    0.50
     newArr
    0.50
     eventType
    0.49
     rowCount
    0.49
    Naissance
    0.48
    Activations Density 2.974%

    No Known Activations