© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11293
    Prev
    Next
    INDEX
    Explanations

    Java "try...catch" blocks

    oai_token-act-pair · gemini-2.0-flash

    catch blocks in code

    np_token-act-pair-logits · gpt-4o-mini

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    z
    -0.49
    UnitTesting
    -0.47
    oredCriteria
    -0.45
     sing
    -0.44
     excesses
    -0.43
    TagHelper
    -0.43
    pre
    -0.43
    link
    -0.43
    ss
    -0.41
    twimg
    -0.41
    POSITIVE LOGITS
     catch
    0.79
     AttributeSet
    0.77
    CATCH
    0.71
     catcher
    0.69
     catching
    0.69
     CATCH
    0.68
    Cyfeiriadau
    0.66
    ंदीखरीदारी
    0.65
    уда
    0.64
    catch
    0.63
    Activations Density 0.181%

    No Known Activations