INDEX

Explanations

mentions of the United States or US government agencies.

oai_token-act-pair · gemini-2.0-flash

United States

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

-0.54

 United

-0.50

orianCalendar

-0.50

setVerticalGroup

-0.47

 White

-0.46

IsMutable

-0.46

MLLoader

-0.45

ChildScrollView

-0.43

ToBounds

-0.42

Datuak

-0.42

POSITIVE LOGITS

 kasarigan

0.76

 بيها

0.67

XmlAccessType

0.67

település

0.63

principalTable

0.63

 Audiodateien

0.58

клопе

0.57

 vérit

0.56

onucleotide

0.56

 pleaſure

0.56

Activations Density 4.414%

mentions of the United States or US government agencies.

United States

No Comments

No Known Activations

mentions of the United States or US government agencies.

United States

No Comments

No Known Activations