INDEX

Explanations

code syntax, especially in Javascript

oai_token-act-pair · gemini-2.0-flash

code

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

<bos>

-0.68

 alternativo

-0.48

ahme

-0.46

ровании

-0.45

amerikanischer

-0.43

่า

-0.43

使

-0.43

rya

-0.41

ful

-0.41

 conveying

-0.41

POSITIVE LOGITS

 насељу

0.75

sidemargin

0.74

TagMode

0.65



0.65

ⓧ

0.64

GEBURTSDATUM

0.63

parsedMessage

0.63

 ویکی‌پدیا

0.61

नलिखित

0.60

Portale

0.60

Activations Density 3.632%

code syntax, especially in Javascript

code

No Comments

No Known Activations