INDEX

Explanations

code-related terms and keywords in Java.

oai_token-act-pair · gemini-2.0-flash

code-related text

np_token-act-pair-logits · gemini-2.0-flash

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

nasse

-0.52

sub

-0.48

 JADX

-0.48

my

-0.47

-0.45

echt

-0.45

nameof

-0.44

our

-0.44

ポスト

-0.44

 Harris

-0.43

POSITIVE LOGITS

 resourceCulture

0.69

SpringBootTest

0.69

:✨

0.63

 indisponible

0.60

 autonomie

0.59

prefixer

0.59

 AssemblyTitle

0.58

smithy

0.58

 Numerade

0.57

 natale

0.57

Activations Density 0.134%

code-related terms and keywords in Java.

code-related text

code

No Comments

No Known Activations