INDEX

Explanations

references to the reader using terms like you, they and people

oai_token-act-pair · gemini-2.0-flash

you

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

Autoritní

-0.85

SharedCtor

-0.68

 kaarangay

-0.68

cemment

-0.68

ंदीखरीदारी

-0.67

igshid

-0.67

tvguidetime

-0.67

 الحره

-0.66

verwijspagina

-0.63

AddHtmlAttribute

-0.63

POSITIVE LOGITS

клопе

0.44

protoc

0.43

rawDesc

0.41

alibaba

0.40

ímite

0.39

 whereof

0.39

poons

0.37

----------

0.36

 CITED

0.36

"),

0.36

Activations Density 7.245%

references to the reader using terms like you, they and people

you

No Comments

No Known Activations