INDEX

Explanations

the word "deep" often with words indicating location, abstract concepts, or strong feelings and sometimes with a negative connotation.

oai_token-act-pair · gemini-2.0-flash

deep

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

httphttps

-0.80

DoubleQuotes

-0.72

 Infórmanos

-0.69

PreferredItem

-0.65

ButterKnife

-0.63

ConstraintMaker

-0.62

 незавершена

-0.60

UseVisualStyle

-0.60

RegistryLite

-0.59

 propOrder

-0.59

POSITIVE LOGITS

يكب

0.44

Cal

0.39

colgroup

0.39

 EdgeInsets

0.39

BuildContext

0.38

sell

0.38

ází

0.38

 work

0.38

Northwest

0.37

deselect

0.37

Activations Density 1.424%

the word "deep" often with words indicating location, abstract concepts, or strong feelings and sometimes with a negative connotation.

deep

No Comments

No Known Activations