INDEX

Explanations

occurrences of the verb "are"

oai_token-act-pair · gemini-2.0-flash

are

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

 itſelf

-1.63

 Jefus

-1.59

 Theſe

-1.58

 Majefty

-1.51

 Monfieur

-1.50

Efq

-1.47

 myſelf

-1.42

 himſelf

-1.42

 themſelves

-1.40

$_"

-1.39

POSITIVE LOGITS

am

1.26

Am

0.79

am

0.76

AM

0.75

im

0.73

Am

0.68

0.66

AM

0.64

0.61

0.60

Activations Density 0.236%

occurrences of the verb "are"

are

No Comments

No Known Activations