INDEX

Explanations

a variety of words and phrases, some related to computing, others to geography, commerce, legal matters, emotions and locations.

oai_token-act-pair · gemini-2.0-flash

Proper nouns and code fragments

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

 butterknife

-0.58

enumi

-0.56

tileno

-0.52

 pstmt

-0.50

PRNewswire

-0.50

Rptr

-0.49

withIdentifier

-0.49

CopyWith

-0.48

peza

-0.48

TabIndex

-0.48

POSITIVE LOGITS

 becauſe

0.82

 Theſe

0.70

 ſmall

0.69

 myſelf

0.67

ness

0.67

expandindo

0.66

 itſelf

0.65

 uſed

0.63

 fevere

0.63

culous

0.61

Activations Density 18.603%

a variety of words and phrases, some related to computing, others to geography, commerce, legal matters, emotions and locations.

Proper nouns and code fragments

No Comments

No Known Activations