INDEX

Explanations

words and phrases related to sales, business, and customer objections

oai_token-act-pair · gemini-2.0-flash

Technical jargon

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

 Normdatei

-0.78

Билгалдахарш

-0.54

contentLoaded

-0.54

kháu

-0.51

 otomatig

-0.50

 linkovi

-0.50

)|^{

-0.49

otoro

-0.48

InjectAttribute

-0.48

Vanjske

-0.48

POSITIVE LOGITS

ⓘ

0.67

SharedCtor

0.61

esModule

0.57

IsContent

0.54

+#+#

0.54

HasColumnType

0.53

Only

0.50

FieldBuilder

0.50

WebElementEntity

0.48

 يتيمه

0.48

Activations Density 1.681%

words and phrases related to sales, business, and customer objections

Technical jargon

No Comments

No Known Activations