INDEX

Explanations

corporate event announcements

oai_token-act-pair · gemini-2.0-flash

code snippets

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

WebVitals

-0.66

 Cité

-0.65

EDEFAULT

-0.63

WriteTagHelper

-0.62

 propOrder

-0.60

expandindo

-0.59

 gynhyrchwyd

-0.57

windowFixed

-0.57

 Theſe

-0.56

PyExc

-0.54

POSITIVE LOGITS

 kaynağından

0.56

MemoryWarning

0.51

--

0.48

\{\\

0.45

ocardio

0.45

 Franz

0.42

 StatefulWidget

0.42

 StatelessWidget

0.41

 assume

0.41

..<

0.41

Activations Density 0.683%

corporate event announcements

code snippets

No Comments

No Known Activations