INDEX

Explanations

phrases associated with providing answers to questions

oai_token-act-pair · gemini-2.0-flash

Answer, colon

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-0.70

ContentAsync

-0.69

ReusableCell

-0.66

TypedDataSet

-0.61

 StatefulWidget

-0.59

 viewType

-0.58

 kasarigan

-0.57

 picioare

-0.57

 useAppContext

-0.57

 Diretto

-0.57

POSITIVE LOGITS

 calendriers

0.52

Notas

0.50

documentclass

0.47

 valueForKey

0.46

motic

0.44

 believe

0.44

InfoWindow

0.43

 querían

0.43

orteur

0.43

 wanted

0.43

Activations Density 0.273%

phrases associated with providing answers to questions

Answer, colon

No Comments

No Known Activations