INDEX

Explanations

words indicating conflict, tension, or pressure associated with political or economic events.

oai_token-act-pair · gemini-2.0-flash

high intensity

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

MigrationBuilder

-0.90

 utafitiHapana

-0.63

&__

-0.60

omitempty

-0.58

 مشين

-0.56

BeforeClass

-0.53

 виправивши

-0.52

inheritdoc

-0.51

blank

-0.51

MENT

-0.51

POSITIVE LOGITS

 heavy

1.48

 strong

1.28

heavy

1.25

Heavy

1.19

 Heavy

1.18

 HEAVY

1.17

 severe

1.13

strong

1.12

 sharp

1.05

 intense

1.02

Activations Density 7.221%

words indicating conflict, tension, or pressure associated with political or economic events.

high intensity

No Comments

No Known Activations