INDEX

Explanations

words broadly related to scientific discourse, often including studies, numbers, and sources

oai_token-act-pair · gemini-2.0-flash

Expressing viewpoints/emotions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 nahilalakip

-0.80

 незавершена

-0.76

 iſt

-0.69

 تانيه

-0.67

ագրություններ

-0.65

 ſche

-0.64

 shewn

-0.63

 Wicidata

-0.61

 صوتيه

-0.60

 Cæsar

-0.60

POSITIVE LOGITS

 relâche

0.50

,:);

0.48

nalités

0.47

UserScript

0.47

TProtocol

0.47

 artificiales

0.46

argo

0.46

 đôi

0.45

kwds

0.43

 chắn

0.42

Activations Density 25.417%

words broadly related to scientific discourse, often including studies, numbers, and sources

Expressing viewpoints/emotions

No Comments

No Known Activations