INDEX

Explanations

code and comments related to floating point and integer operations

oai_token-act-pair · gemini-2.0-flash

floating point numbers in code

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

 Floating

-2.06

 floating

-2.03

 floats

-2.02

 float

-1.98

Floating

-1.89

 Float

-1.85

floating

-1.81

 floated

-1.81

 FLOAT

-1.78

float

-1.67

POSITIVE LOGITS

enumi

0.50

 مشين

0.47

 russes

0.46

rav

0.42

Den

0.42

ViewImports

0.42

円

0.41

 européennes

0.40

DIRS

0.39

Den

0.38

Activations Density 2.102%

code and comments related to floating point and integer operations

floating point numbers in code

No Comments

No Known Activations