INDEX

Explanations

words relating to purchasing items or religious offerings

oai_token-act-pair · gemini-2.0-flash

Worship/Rituals/Necessities

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

 referenties

-0.61

änien

-0.55

 Wicidata

-0.52

ystis

-0.49

NameInMap

-0.49

Források

-0.47

 Biôgrafia

-0.46

 esternos

-0.46

ApiModelProperty

-0.46

ZN

-0.45

POSITIVE LOGITS

ViewChild

0.67

 AttributeSet

0.62

 AssemblyTitle

0.60

 intptr

0.54

PullParser

0.51

 steels

0.51

ArgsConstructor

0.47

termilk

0.47

equation

0.47

tellungs

0.47

Activations Density 4.775%

words relating to purchasing items or religious offerings

Worship/Rituals/Necessities

No Comments

No Known Activations