INDEX

Explanations

the prefix "de" in different contexts

oai_token-act-pair · gemini-2.0-flash

de

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

ležit

-0.51

◄

-0.51

رشف

-0.51

пита

-0.50

">//

-0.50

copyFrom

-0.49

ΐ

-0.48

iella

-0.47

reading

-0.47

ʁ

-0.47

POSITIVE LOGITS

 '\\;'

0.71

MENAFN

0.69

Autoritní

0.65

 pleaſure

0.64

NewUrlParser

0.60

 myſelf

0.59

 doubtnut

0.59

InitVars

0.58

Externí

0.57

ſelves

0.57

Activations Density 0.579%

the prefix "de" in different contexts

de

No Comments

No Known Activations