INDEX

Explanations

code diffs and equation alignment symbols

oai_token-act-pair · gemini-2.0-flash

& and -

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

Efq

-0.96

IntoConstraints

-0.95

 NDEBUG

-0.94

 doubtnut

-0.85

SupportActionBar

-0.84

MessageTagHelper

-0.83

 Мексичка

-0.80

 Houſe

-0.79

ArgsConstructor

-0.79

ſelf

-0.79

POSITIVE LOGITS

The

0.52

tabular

0.47

Bibliograf

0.46

do

0.41

…

0.41

Do

0.40

̣n

0.40

↵↵

0.39

...

0.39

me

0.39

Activations Density 0.391%

code diffs and equation alignment symbols

& and -

No Comments

No Known Activations