INDEX

Explanations

the partial word "Gu". Specifically, it seems to be keying in on Guyana and related words

oai_token-act-pair · gemini-2.0-flash

Gu

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

AddHtmlAttribute

-0.77

fillType

-0.65

 nahilalakip

-0.58

ISupport

-0.53

AddTagHelper

-0.50

 postIndex

-0.47

 وتسجيلات

-0.47

VIAF

-0.45

 isComment

-0.44

stateProvider

-0.44

POSITIVE LOGITS

Efq

0.77

 ſmall

0.75

 whoſe

0.74

 myſelf

0.72

 ſeveral

0.71

 pleaſure

0.67

 itſelf

0.66

 Monfieur

0.66

 faſt

0.65

 himſelf

0.63

Activations Density 0.329%

the partial word "Gu". Specifically, it seems to be keying in on Guyana and related words

Gu

No Comments

No Known Activations