INDEX

Explanations

Spanish and Portuguese words as well as words containing "tu"

oai_token-act-pair · gemini-2.0-flash

Non-English language

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 /\.(

-0.56

jang

-0.45

Enllaces

-0.45

multirow

-0.45

urlpatterns

-0.43

TCHAR

-0.43

variates

-0.43

 NgModule

-0.43

 PropTypes

-0.42

</tfoot>

-0.41

POSITIVE LOGITS

 here

1.55

here

1.37

Here

1.27

 Here

1.27

Здесь

1.25

HERE

1.25

 burada

1.24

 aici

1.23

 HERE

1.21

 aquí

1.20

Activations Density 0.379%

Spanish and Portuguese words as well as words containing "tu"

Non-English language

No Comments

No Known Activations

Spanish and Portuguese words as well as words containing "tu"

Non-English language

No Comments

No Known Activations