INDEX

Explanations

content in Spanish and related to the European Union or government funding

oai_token-act-pair · gemini-2.0-flash

multiple languages

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

########.

-0.38

וויק

-0.36

مصادر

-0.35

ting

-0.32

Obituary

-0.32

像

-0.32

 tart

-0.31

neh

-0.31

RTLU

-0.31

Source

-0.31

POSITIVE LOGITS

 resourceCulture

0.93

 protoimpl

0.87

 دیکھیے

0.84

expandindo

0.84

MLLoader

0.80

sizeCache

0.80

клопе

0.79

:✨

0.79

 الرياضيه

0.79

IVEREF

0.78

Activations Density 1.075%

content in Spanish and related to the European Union or government funding

multiple languages

No Comments

No Known Activations