INDEX

Explanations

instances of the word "and" alone or in common phrases surrounding multiple events

oai_token-act-pair · gemini-2.0-flash

and

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

Out

-0.48

Is

-0.47

En

-0.47

Out

-0.46

!",

-0.46

Or

-0.45

"!

-0.44

”!

-0.44

",

-0.43

>),

-0.43

POSITIVE LOGITS

ագրություններ

0.75

Бележки

0.75

LEncoder

0.71

 Tagore

0.69

afety

0.68

 wikihow

0.67

 Taro

0.65

 unmute

0.64

GGLE

0.64

 consultato

0.64

Activations Density 16.057%

instances of the word "and" alone or in common phrases surrounding multiple events

and

No Comments

No Known Activations