INDEX

Explanations

Java code files containing import and util statements paired with version numbers

oai_token-act-pair · gemini-2.0-flash

Java code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Kits

-0.51

 Shoulders

-0.49

kit

-0.48

vaders

-0.48

 Signalez

-0.48

ressee

-0.47

馃

-0.46

 atter

-0.46

 Fell

-0.46

 insensible

-0.46

POSITIVE LOGITS

XmlAccessType

0.80

NgModule

0.64

featureID

0.63

EditorBrowsable

0.58

 étoient

0.57

XMLSchema

0.57

XSSF

0.56

ecore

0.56

openConnection

0.56

sequelize

0.56

Activations Density 1.874%

Java code files containing import and util statements paired with version numbers

Java code

No Comments

No Known Activations