INDEX

Explanations

articles and words like "primary", "basic", "most", and "big", especially when combined with "the"

oai_token-act-pair · gemini-2.0-flash

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

rungsseite

-0.70

pushFollow

-0.59

wiſe

-0.57

Izvori

-0.56

DCA

-0.54

griff

-0.54

 doInBackground

-0.53

iffance

-0.52

 onData

-0.52

msgTypes

-0.52

POSITIVE LOGITS

thâu

0.82

SourceChecksum

0.54

 WARREN

0.51

 compass

0.50

ثيق

0.46

ariConfig

0.45

المناصب

0.44

 expli

0.44

MemoryWarning

0.44

IVEREF

0.43

Activations Density 0.539%

articles and words like "primary", "basic", "most", and "big", especially when combined with "the"

the

No Known Activations