INDEX

Explanations

loans

np_max-act-logits · gemini-2.0-flash

words and phrases involving money and debt.

oai_token-act-pair · gemini-2.0-flash

loans

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 lender

-0.68

 lenders

-0.68

 propOrder

-0.65

 bankers

-0.64

 loans

-0.62

ReusableCell

-0.62

참고

-0.61

loans

-0.61

loan

-0.59

Loan

-0.59

POSITIVE LOGITS

rawDesc

0.52

 SDLK

0.51

deleteUser

0.45

 deleteUser

0.45

 màn

0.44

 keyPressed

0.44

 ويكيپيديا

0.43

UIControl

0.42

sqcup

0.41

uze

0.41

Activations Density 3.031%

loans

words and phrases involving money and debt.

loans

No Comments

No Known Activations