INDEX

Explanations

the word 'Please'

oai_token-act-pair · gemini-2.0-flash

Please

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ImageContext

-0.84

 pleaſure

-0.81

 contextLoads

-0.77

TintMode

-0.75

 houſe

-0.74

contentLoaded

-0.71

ISupport

-0.71

AccessorTable

-0.70

 utafitiHapana

-0.69

SharedDtor

-0.69

POSITIVE LOGITS

don

0.75

don

0.56

bor

0.52

ؤلاء

0.51

th

0.50

 dont

0.50

em

0.49

see

0.48

 aren

0.48

Don

0.47

Activations Density 0.315%

the word 'Please'

Please

No Comments

No Known Activations