INDEX

Explanations

words and phrases used for describing how groups of people work together to handle something numerically

oai_token-act-pair · gemini-2.0-flash

numbers

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

parsedMessage

-1.06

BibitemShut

-1.01

^(@)

-0.97

 ―――――

-0.96

脚注の使い方

-0.94

 ſind

-0.93

 Theſe

-0.93

NUMX

-0.92

 فريبيس

-0.91

Efq

-0.91

POSITIVE LOGITS

0.79

six

0.63

 seven

0.57

 nine

0.57

 eight

0.56

 five

0.55

 four

0.55

up

0.49

0.48

 cuatro

0.47

Activations Density 3.183%

words and phrases used for describing how groups of people work together to handle something numerically

numbers

No Comments

No Known Activations