INDEX

Explanations

the characters "Shi" appearing in the text

oai_token-act-pair · gemini-2.0-flash

Shi

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

WebServlet

-0.64

енча

-0.63

BrowserModule

-0.54

setVerticalGroup

-0.51

jbl

-0.50

 Fair

-0.49

UnsafeEnabled

-0.49

mickey

-0.48

contentLoaded

-0.47

 body

-0.47

POSITIVE LOGITS

WriteTagHelper

0.72

abetes

0.61

enumi

0.58

GraphicsUnit

0.56

 שוליים

0.55

geno

0.54

 <<<<<<<<<<<<<<

0.54

/*---

0.54

}],

0.53

jewództ

0.52

Activations Density 0.394%

the characters "Shi" appearing in the text

Shi

No Comments

No Known Activations