INDEX

Explanations

code or shopping list items, often using the word "item"

oai_token-act-pair · gemini-2.0-flash

item

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

IndentedString

-0.78

Espèce

-0.70

 Wikimedijinoj

-0.70

 Савезне

-0.70

 المعيارى

-0.68

 betweenstory

-0.67

ArrowToggle

-0.66

 ſeveral

-0.65

 fubject

-0.64

 pleaſure

-0.62

POSITIVE LOGITS

acs

0.48

 considérons

0.45

ването

0.41

 that

0.41

WEBPACK

0.40

ote

0.39

सू

0.39

gid

0.38

non

0.38

å

0.38

Activations Density 12.300%

code or shopping list items, often using the word "item"

item

No Known Activations