INDEX

Explanations

terms, abbreviations, or labels used in a scientific study.

oai_token-act-pair · gemini-2.0-flash

Viral protein research

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

kloped

-0.71

 autorytatywna

-0.68

cyklopedia

-0.67

setVerticalGroup

-0.63

 fieldNum

-0.61

findpost

-0.60

RegressionTest

-0.60

 ویکی‌آمباردا

-0.58

 postIndex

-0.57

cstdio

-0.57

POSITIVE LOGITS

 déri

0.47

 lumineuse

0.45

spunkt

0.45

SocketAddress

0.44

 Correa

0.44

]='\

0.43

Imported

0.43

 gynnwys

0.41

TargetException

0.41

 fevere

0.40

Activations Density 2.786%

terms, abbreviations, or labels used in a scientific study.

Viral protein research

No Comments

No Known Activations