INDEX

Explanations

mentions of universities and hospitals

oai_token-act-pair · gemini-2.0-flash

Web article snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

cat

-0.47

 post

-0.44

ⓧ

-0.43

post

-0.42

Nature

-0.41

 hObject

-0.40

cat

-0.40

 fenómenos

-0.40

Cat

-0.40

Cat

-0.40

POSITIVE LOGITS

évaluateur

0.72

Carriera

0.71

ValueStyle

0.71

 оригіналу

0.68

 Reſ

0.65

igurumi

0.65

 iſt

0.64

 ſtand

0.64

 betweenstory

0.63

 myſelf

0.63

Activations Density 0.866%

mentions of universities and hospitals

Web article snippets

No Comments

No Known Activations