INDEX

Explanations

LaTeX code

oai_token-act-pair · gemini-2.0-flash

usepackage

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

InputBorder

-0.69

存于互联网档案馆

-0.69

 ddelweddau

-0.65

rometry

-0.64

webElementGuid

-0.63

ConverterFactory

-0.62

 NSCoder

-0.61

balleur

-0.60

ArgsConstructor

-0.60

Démographie

-0.58

POSITIVE LOGITS

<bos>

1.91

The

0.44

run

0.40

 move

0.40

the

0.40

An

0.39

Max

0.37

0.36

To

0.36

Ten

0.36

Activations Density 0.174%

LaTeX code

usepackage

No Comments

No Known Activations