INDEX

Explanations

the word "clinical", especially when it occurs nearby words related to research studies or logic

oai_token-act-pair · gemini-2.0-flash

clinical

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 larmes

-0.56

expandindo

-0.54

 jScrollPane

-0.53

 cloning

-0.52

Cre

-0.52

NameInMap

-0.52

olom

-0.50

ToAction

-0.50

 marbre

-0.50

 promozione

-0.49

POSITIVE LOGITS

MENAFN

0.76

 ControllerBase

0.66

 שוליים

0.59

 '\\;'

0.59

izoen

0.57

principalColumn

0.57

aarrggbb

0.56

oa̍t

0.51

期刊论文

0.50

 famí

0.49

Activations Density 0.994%

the word "clinical", especially when it occurs nearby words related to research studies or logic

clinical

No Comments

No Known Activations