INDEX

Explanations

character encodings of different versions

oai_token-act-pair · gemini-2.0-flash

UTF

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

Not in Any Lists

No Comments

Negative Logits

ContentAsync

-0.68

 مشين

-0.64

TagMode

-0.60

 InputDecoration

-0.56

formik

-0.54

traceback

-0.54

RenderAtEndOf

-0.53

 chi̍t

-0.53

Życiorys

-0.52

ագրություններ

-0.52

POSITIVE LOGITS

 ujednoznacz

0.65

تقاوى

0.52

saraba

0.52

BELL

0.49

PCell

0.47

imetsu

0.47

軋

0.47

Rinse

0.46

 capitals

0.45

 alde

0.45

Activations Density 0.141%

character encodings of different versions

UTF

No Comments

No Known Activations