INDEX

Explanations

hedging language about future plans

oai_token-act-pair · gemini-2.0-flash

to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

MemoryWarning

-0.64

 старости

-0.60

OrNil

-0.58

ChildScrollView

-0.57

ValueStyle

-0.57

ɵ

-0.55

 تضيفلها

-0.54

localctx

-0.53

RegistryLite

-0.52

 estekak

-0.51

POSITIVE LOGITS

formin

0.55

contentLoaded

0.48

ForValue

0.47

 ISNI

0.46

PathVariable

0.46

Powered

0.46

 smtplib

0.45

 androidx

0.45

TRIBUN

0.44

 كورة

0.44

Activations Density 3.185%

hedging language about future plans

to

No Comments

No Known Activations