INDEX

Explanations

words related to education, real estate and internet browsing with high sensitivity to the word 'level'

oai_token-act-pair · gemini-2.0-flash

scale/variation

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

 venons

-0.75

 varandra

-0.73

 sociaux

-0.68

 pleaſure

-0.65

 vectorielle

-0.65

 termica

-0.64

 ſmall

-0.63

 fotografico

-0.63

 aveug

-0.60

 Argyle

-0.60

POSITIVE LOGITS

setCellValue

0.54

fono

0.48

reactstrap

0.48

 Wicidata

0.46

 else

0.44

 XCTest

0.43

ënt

0.43

Mic

0.42

else

0.42

 Pers

0.42

Activations Density 46.459%

words related to education, real estate and internet browsing with high sensitivity to the word 'level'

scale/variation

No Comments

No Known Activations