INDEX

Explanations

words, phrases, and acronyms related to reports, research and legal documents

oai_token-act-pair · gemini-2.0-flash

show

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

กัน

-0.43

-0.42

ana

-0.38

<eos>

-0.37

ix

-0.37

db

-0.37

di

-0.36

メイ

-0.36

iace

-0.36

transQ

-0.36

POSITIVE LOGITS

 show

2.47

 showing

2.41

 shows

2.41

 Showing

2.33

 Shows

2.31

shows

2.31

show

2.25

showing

2.25

SHOW

2.23

 Show

2.20

Activations Density 5.615%

words, phrases, and acronyms related to reports, research and legal documents

show

No Comments

No Known Activations