INDEX

Explanations

words and prefixes beginning with 'un' and other vowel-initiated prefixes and suffixes, as well as some accented characters

oai_token-act-pair · gemini-2.0-flash

un- prefix

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ainfi

-1.54

 Monfieur

-1.32

 Anſ

-1.31

Efq

-1.31

 fidé

-1.25

 étoient

-1.24

 Reſ

-1.21

 iſt

-1.21

 auffi

-1.20

 avoient

-1.20

POSITIVE LOGITS

un

1.20

1.00

le

0.96

0.93

une

0.93

Un

0.90

una

0.85

Le

0.85

la

0.84

el

0.83

Activations Density 1.016%

words and prefixes beginning with 'un' and other vowel-initiated prefixes and suffixes, as well as some accented characters

un- prefix

No Comments

No Known Activations