INDEX

Explanations

text artifacts such as unexpected spaces in the middle of a word or sentences starting with "Wery"

oai_token-act-pair · 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

 المعيارى

-0.91

 وتسجيلات

-0.90

IUrlHelper

-0.77

Билгалдахарш

-0.75

__(/*!

-0.75

!*\

-0.74

 cherchés

-0.72

rungsseite

-0.72

Зноскі

-0.71

 CreateTagHelper

-0.71

POSITIVE LOGITS

 comigo

0.49

 włosy

0.48

 książki

0.48

rova

0.48

 męskie

0.46

řel

0.46

 independientes

0.46

ailles

0.45

 uuidv

0.45

trische

0.45

Activations Density 0.159%

text artifacts such as unexpected spaces in the middle of a word or sentences starting with "Wery"

No Comments

No Known Activations