INDEX

Explanations

numbers and mathematical notation with a dollar sign nearby

oai_token-act-pair · gemini-2.0-flash

code and equations

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

 piú

-0.66

 preuves

-0.51

 kılıf

-0.51

 creș

-0.50

 peggio

-0.49

 médicaments

-0.48

 paramètres

-0.48

 conséquences

-0.47

 danni

-0.47

 curieux

-0.47

POSITIVE LOGITS

ContentAlignment

0.99

TagMode

0.93

cách

0.85

Viited

0.84

tôi

0.81

SequentialGroup

0.79

 فريبيس

0.79

Màu

0.78

+#+#

0.77

học

0.77

Activations Density 10.941%

numbers and mathematical notation with a dollar sign nearby

code and equations

No Comments

No Known Activations