INDEX

Explanations

auxiliary verbs, especially "have" and "has", along with some nouns and adjectives.

oai_token-act-pair · gemini-2.0-flash

has

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

PRNewswire

-0.60

זרה

-0.57

 directiva

-0.49

 مواليد

-0.48

ništvo

-0.47

AttributeSet

-0.46

 followed

-0.46

vaadin

-0.45

imel

-0.45

hant

-0.45

POSITIVE LOGITS

 kaynağından

0.73

 ivelany

0.60

Дереккөздер

0.60

 الرياضيه

0.58

 Pyram

0.57

Izvori

0.53

Estr

0.52

 مرئيه

0.52

Билгалдахарш

0.52

WireFormatLite

0.51

Activations Density 14.078%

auxiliary verbs, especially "have" and "has", along with some nouns and adjectives.

has

No Comments

No Known Activations