INDEX

Explanations

delimiters, conditional statements, and sizing

oai_token-act-pair · gemini-2.0-flash

not

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

Not in Any Lists

No Comments

Negative Logits

 endwhile

-0.66

 propOrder

-0.62

 متعلقه

-0.57

@"/

-0.54

 ujednoznacz

-0.54

 protoimpl

-0.54

urably

-0.53

CppMethod

-0.52

 تضيفلها

-0.51

queryInterface

-0.50

POSITIVE LOGITS

not

1.66

 nicht

1.38

 não

1.31

 niet

1.29

not

1.23

 wasn

1.23

 не

1.18

NOT

1.17

isn

1.17

Not

1.17

Activations Density 2.219%

delimiters, conditional statements, and sizing

not

No Comments

No Known Activations