INDEX

Explanations

words related to computer hardware and electronics

oai_token-act-pair · gemini-2.0-flash

Computer architecture

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

 فريبيس

-0.71

 Jefus

-0.71

 <=",

-0.65

 Theſe

-0.65

QMetaType

-0.63

 raiſ

-0.63

Дереккөздер

-0.61

Zad

-0.60

 elettrica

-0.59

 elettrico

-0.58

POSITIVE LOGITS

تقاوى

0.56

Arm

0.54

0.51

دانشنامهٔ

0.50

eleste

0.47

ARM

0.47

Arm

0.46

JEL

0.45

ONG

0.44

 επί

0.43

Activations Density 1.224%

words related to computer hardware and electronics

Computer architecture

No Comments

No Known Activations