INDEX

Explanations

code in the Java or React languages, with a focus on constructors and inheritance ("super")

oai_token-act-pair · gemini-2.0-flash

code

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

addCriterion

-0.65

ca

-0.50

 насеље

-0.49

Pri

-0.48

Sab

-0.47

더

-0.47

WARDS

-0.46

лежа

-0.45

備

-0.45

POSITIVE LOGITS

اریخ

0.66

 Diretto

0.59

 MusicBrainz

0.58

OGND

0.56

 stihl

0.54

 baptized

0.54

expandindo

0.54

 SafeMath

0.54

 AssemblyCulture

0.54

,$_

0.52

Activations Density 0.497%

code in the Java or React languages, with a focus on constructors and inheritance ("super")

code

No Comments

No Known Activations