INDEX

Explanations

words related to product descriptions and code

oai_token-act-pair · gemini-2.0-flash

code/symbols

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

:✨

-0.93

Попис

-0.76

createClass

-0.59

setLayoutManager

-0.59

 îna

-0.59

 للمعارف

-0.58

strophy

-0.56

 înal

-0.54

 Morty

-0.54

withIdentifier

-0.54

POSITIVE LOGITS

 links

0.51

menter

0.49

bolic

0.45

 handles

0.44

üyada

0.44

stylers

0.43

 poda

0.43

örd

0.42

&__

0.42

tage

0.41

Activations Density 26.532%

words related to product descriptions and code

code/symbols

No Comments

No Known Activations