INDEX

Explanations

code-related keywords such as "string", "min", "max", "decode", and "current".

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

bootstrapcdn

-0.63

AsUp

-0.60

AddField

-0.50

XmlAccessType

-0.49

'][]

-0.46

 leggi

-0.46

SpringRunner

-0.44

 numberWith

-0.44

DoubleQuotes

-0.44

="@+

-0.42

POSITIVE LOGITS

VIAF

0.75

oredCriteria

0.62

 Biôgrafia

0.62

 мәкал

0.59

цездатний

0.57

vedic

0.56

RegressionTest

0.55

NameInMap

0.54

RTEE

0.52

 VIAF

0.51

Activations Density 1.288%

code-related keywords such as "string", "min", "max", "decode", and "current".

code snippets

No Comments

No Known Activations