INDEX

Explanations

instances of ending or preventing something

oai_token-act-pair · gemini-2.0-flash

stopping

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

BeginContext

-0.68

ंदीखरीदारी

-0.64

клопе

-0.58

зулта

-0.55

 useStyles

-0.54

مراجع

-0.51

Referències

-0.50

WaitGroup

-0.48

المراجع

-0.48

 referenties

-0.47

POSITIVE LOGITS

 stop

1.02

 stopping

0.90

stop

0.84

 Stop

0.83

 STOP

0.81

Stop

0.80

Stopping

0.78

 stoppage

0.78

 shut

0.78

 stops

0.77

Activations Density 1.778%

instances of ending or preventing something

stopping

No Comments

No Known Activations