INDEX

Explanations

the word "in" and adjacent words

oai_token-act-pair · gemini-2.0-flash

In

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 nonatomic

-0.77

 >=",

-0.74

 autorytatywna

-0.73

exitRule

-0.72

 awakeFromNib

-0.70

ValueGenerated

-0.68

makeConstraints

-0.67

nonatomic

-0.66

\{\\

-0.65

 podjela

-0.63

POSITIVE LOGITS

 times

0.50

case

0.45

 correctes

0.44

 cases

0.43

 case

0.41

ido

0.41

 cose

0.38

ன்று

0.38

 casos

0.38

 kasus

0.38

Activations Density 0.466%

the word "in" and adjacent words

In

No Comments

No Known Activations