INDEX

Explanations

scientific research or studies

oai_token-act-pair · gemini-2.0-flash

"in" in other languages

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

MigrationBuilder

-0.60

complexType

-0.56

akyti

-0.55

 lenker

-0.54

:+:

-0.52

 GetEnumerator

-0.52

numerusform

-0.52

Personensuche

-0.51

 forState

-0.51

 jScrollPane

-0.50

POSITIVE LOGITS

in

2.70

in

1.42

ใน

1.36

в

1.27

 dalam

1.25

In

1.23

 في

1.23

 در

1.22

în

1.15

In

1.10

Activations Density 14.399%

scientific research or studies

"in" in other languages

No Comments

No Known Activations