INDEX

Explanations

words and phrases related to gratitude and thanking someone

oai_token-act-pair · gemini-2.0-flash

support

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Theſe

-0.59

AndEndTag

-0.59

lunda

-0.58

 يتيمه

-0.56

 myſelf

-0.52

 CreateTagHelper

-0.52

swire

-0.52

 Beſ

-0.50

 NUKAT

-0.50

 hashtag

-0.50

POSITIVE LOGITS

TintMode

0.66

0.64

RegressionTest

0.64

fortawesome

0.59

__*/

0.57

MemoryWarning

0.52

########.

0.51

!!!

0.50

0.48

Activations Density 3.310%

words and phrases related to gratitude and thanking someone

support

No Comments

No Known Activations