INDEX

Explanations

negative statements about what someone can or cannot do, coupled with an object

oai_token-act-pair · gemini-2.0-flash

human experience

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ValueStyle

-0.68

-0.61

łk

-0.58

-0.56

Datuak

-0.55

########.

-0.54

 nakalista

-0.54

 onCancelled

-0.54

ClientRect

-0.54

RegistryLite

-0.54

POSITIVE LOGITS

 ziren

0.54

">"

0.52

richTextPanel

0.50

","

0.50

assertAll

0.49

."]

0.49

atiles

0.49

internalType

0.48

ագրություններ

0.48

parsedMessage

0.48

Activations Density 0.789%

negative statements about what someone can or cannot do, coupled with an object

human experience

No Comments

No Known Activations