INDEX

Explanations

the word "a" modifying an adjective or adverb

oai_token-act-pair · gemini-2.0-flash

Random Text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.66

uação

-0.60

 Oxide

-0.60

 /\.(

-0.58

AnimationsModule

-0.57

 Infórmanos

-0.56

 oxide

-0.56

 Assyrian

-0.53

mmä

-0.53

全文

-0.53

POSITIVE LOGITS

AntiForgeryToken

0.51

 виправивши

0.49

izarse

0.48

 rangs

0.46

قایناق‌لار

0.45

<!--[

0.45

msgSender

0.44

DockStyle

0.43

ppery

0.42

ingeki

0.42

Activations Density 0.900%

the word "a" modifying an adjective or adverb

Random Text

No Comments

No Known Activations