INDEX

Explanations

legal, medical and political terms and language

oai_token-act-pair · gemini-2.0-flash

legal/formal

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 समीक्षक

-0.67

 متعلقه

-0.65

 fubject

-0.60

bootstrapcdn

-0.58

 poffible

-0.57

^(@)

-0.57

يكب

-0.56

ępnie

-0.56

 الرياضيه

-0.55

 pleaſure

-0.55

POSITIVE LOGITS

<bos>

0.83

MigrationBuilder

0.61

detectChanges

0.52

/******/

0.52

SharedCtor

0.50

<eos>

0.47

 Савезне

0.47

 <>",

0.47

########.

0.46

 createState

0.46

Activations Density 49.891%

legal, medical and political terms and language

legal/formal

No Comments

No Known Activations