INDEX

Explanations

parts of Java code that import Android libraries

oai_token-act-pair · gemini-2.0-flash

Code snippets

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

yet

-0.49

ophile

-0.48

の

-0.47

fta

-0.45

ła

-0.45

的

-0.45

pod

-0.45

Kid

-0.45

ικα

-0.44

Pod

-0.44

POSITIVE LOGITS

 EconPapers

0.83

 }}"></

0.77

IndentedString

0.73

 <<<<<<<<<<<<<<

0.72

DockStyle

0.71

LookAnd

0.70

parsedMessage

0.69

 виправивши

0.66

 AssemblyCulture

0.66

.*")]

0.65

Activations Density 0.068%

parts of Java code that import Android libraries

Code snippets

No Comments

No Known Activations