INDEX

Explanations

the word "Value" and code-related terms in various programming languages

oai_token-act-pair · gemini-2.0-flash

say '='

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

StoryboardSegue

-0.90

 propOrder

-0.89

Tikang

-0.80

 насељу

-0.80

 disambiguazione

-0.78

tanleria

-0.78

featureID

-0.76

Diweddarwch

-0.74

CompleteListener

-0.73

 EconPapers

-0.71

POSITIVE LOGITS

0.57

0.40

==

0.39

CrossRef

0.38

 diren

0.37

ınt

0.36

 ejus

0.34

setAccessible

0.33

 diras

0.32

atek

0.32

Activations Density 2.657%

the word "Value" and code-related terms in various programming languages

say '='

No Comments

No Known Activations