INDEX

Explanations

language related to engineering, construction and manufacturing

oai_token-act-pair · gemini-2.0-flash

site

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Cryptography

-0.67

ArrowToggle

-0.57

ReusableCell

-0.56

="{{

-0.51

 télé

-0.50

ocyclic

-0.48

 StatelessWidget

-0.47

УДК

-0.47

dió

-0.47

typeorm

-0.47

POSITIVE LOGITS

 site

1.54

site

1.45

 Site

1.43

Site

1.41

 SITE

1.26

 sites

1.22

 Sites

1.19

SITE

1.16

Sites

1.05

 SITES

1.02

Activations Density 4.929%

language related to engineering, construction and manufacturing

site

No Comments

No Known Activations