INDEX

Explanations

occurrences of numbers or measurements appearing close to specific keywords

oai_token-act-pair · gemini-2.0-flash

technical/academic text

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

-2.08

১

-0.98

１

-0.93

१

-0.79

১

-0.78

 fifteenth

-0.67

١

-0.65

 fourteenth

-0.63

۱

-0.63

 thirteenth

-0.63

POSITIVE LOGITS

RenderAtEndOf

0.85

InjectAttribute

0.69

WebElementEntity

0.69

 يتيمه

0.68

WithIOException

0.64

 >=",

0.62

SourceChecksum

0.62

 pinulongan

0.62

ंदीखरीदारी

0.62

GEBURTSDATUM

0.62

Activations Density 4.285%

occurrences of numbers or measurements appearing close to specific keywords

technical/academic text

No Comments

No Known Activations