INDEX

Explanations

code or game development text

oai_token-act-pair · gemini-2.0-flash

Code/technical snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

TypedDataSet

-0.80

 المعيارى

-0.69

 '\\;'

-0.61

aniya

-0.60

 تضيفلها

-0.58

 مرئيه

-0.57

 متعلقه

-0.57

GraphicsUnit

-0.57

TagMode

-0.55

transQ

-0.55

POSITIVE LOGITS

 slide

0.53

 Parad

0.50

 Gregor

0.49

 barrels

0.49

 mapStateToProps

0.49

 sever

0.47

 الدولى

0.47

udi

0.47

phie

0.46

slide

0.46

Activations Density 6.411%

code or game development text

Code/technical snippets

No Comments

No Known Activations