INDEX

Explanations

phrases indicating a good time to do something

oai_token-act-pair · gemini-2.0-flash

is

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

تقاوى

-0.61

]--;

-0.60

 للاسماء

-0.59

toHaveBeenCalled

-0.57

KommentareTeilen

-0.56

VersionUID

-0.56

 متعلقه

-0.55

 ModelExpression

-0.54

 onResponse

-0.52

JNIEnv

-0.52

POSITIVE LOGITS

is

2.38

isn

1.27

was

1.20

 adalah

1.12

Is

1.09

 isnt

1.00

 είναι

1.00

là

0.99

is

0.94

IS

0.94

Activations Density 1.487%

phrases indicating a good time to do something

is

No Comments

No Known Activations