INDEX

Explanations

technical jargon from scientific publications

oai_token-act-pair · gemini-2.0-flash

Abbreviations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 quæ

-0.69

The

-0.66

 Each

-0.62

 Both

-0.61

 ویکی‌پدیا

-0.60

 Similarly

-0.60

 Either

-0.60

The

-0.58

 Neither

-0.57

Each

-0.57

POSITIVE LOGITS

MCS

0.51

TSS

0.50

Cd

0.48

álva

0.48

ECM

0.48

QRect

0.48

CCM

0.47

TOC

0.45

CTR

0.45

TMS

0.45

Activations Density 41.483%

technical jargon from scientific publications

Abbreviations

No Comments

No Known Activations