INDEX

Explanations

the phrases "has been" or "is still"

oai_token-act-pair · gemini-2.0-flash

been

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

Negative Logits

fromCharCode

-0.50

Geplaatst

-0.47

 محفوظة

-0.47

لع

-0.46

HostException

-0.44

ARS

-0.44

autant

-0.43

ars

-0.43

moveToFirst

-0.43

hikari

-0.42

POSITIVE LOGITS

 existed

0.94

 exists

0.81

 exist

0.81

afficheront

0.75

PreferredItem

0.75

 EXIST

0.75

 surla

0.74

évaluateur

0.73

 EClass

0.73

 existence

0.71

Activations Density 0.669%

the phrases "has been" or "is still"

been

No Known Activations