INDEX

Explanations

the characters "hi" outside of common words, which could possibly be associated with code or greetings

oai_token-act-pair · gemini-2.0-flash

hi

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dia

-0.45

lo

-0.45

da

-0.44

los

-0.43

chen

-0.40

lott

-0.40

cum

-0.40

ya

-0.40

le

-0.40

cu

-0.39

POSITIVE LOGITS

twimg

0.83

UIControlState

0.81

adpleegd

0.79

 Réponses

0.77

withIdentifier

0.75

ViewFeatures

0.75

AddTagHelper

0.74

 CreateTagHelper

0.71

 تضيفلها

0.70

 endwhile

0.68

Activations Density 0.377%

the characters "hi" outside of common words, which could possibly be associated with code or greetings

hi

No Comments

No Known Activations