INDEX

Explanations

snippets of computer code

oai_token-act-pair · gemini-2.0-flash

Code punctuation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

^(@)

-1.62

 myſelf

-1.59

 Савезне

-1.54

 ainfi

-1.54

ſelf

-1.48

 auffi

-1.48

berdayakan

-1.47

 autorytatywna

-1.47

 Majefty

-1.47

 iſt

-1.46

POSITIVE LOGITS

0.61

0.50

0.48

0.44

↵↵

0.43

0.42

0.40

’

0.40

0.39

0.38

Activations Density 2.942%

snippets of computer code

Code punctuation

No Comments

No Known Activations