INDEX

Explanations

words related to obtaining assistance and expressing gratitude.

oai_token-act-pair · gemini-2.0-flash

Thanks and requests

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

Wut

-0.54

ἶ

-0.51

chiali

-0.49

principal

-0.48

leveland

-0.48

iläum

-0.46

sibili

-0.46

tabilis

-0.46

UITableViewCell

-0.46

 principal

-0.45

POSITIVE LOGITS

MigrationBuilder

0.75

UnusedPrivate

0.69

#+#

0.65

awtextra

0.62

PageRoute

0.62

 resourceCulture

0.62

complexContent

0.61

 насељу

0.58

 MotionEvent

0.57

 Ceramby

0.57

Activations Density 1.960%

words related to obtaining assistance and expressing gratitude.

Thanks and requests

No Comments

No Known Activations