INDEX

Explanations

the word "you"

oai_token-act-pair · gemini-2.0-flash

you

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

 IBOutlet

-0.93

RectangleBorder

-0.87

ThroughAttribute

-0.79

 protoimpl

-0.71

RequestMapping

-0.64

QPalette

-0.62

RestController

-0.62

adaptiveStyles

-0.61

 &___

-0.61

 ProtoMessage

-0.61

POSITIVE LOGITS

<bos>

0.64

 Paglinawan

0.61

헌

0.46

सन्दर्भ

0.45

ABUL

0.44

 lần

0.44

FileDialog

0.44

entieth

0.43

RegressionTest

0.42

лько

0.41

Activations Density 21.341%

the word "you"

you

No Comments

No Known Activations