INDEX

Explanations

prepositions

oai_token-act-pair · gemini-2.0-flash

string

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

IndentedString

-0.77

 CreateTagHelper

-0.76

phrag

-0.73

BeginContext

-0.67

ApiModel

-0.64

 bershka

-0.63

ükemmel

-0.62

"}")

-0.61

pexpr

-0.61

Autoritní

-0.60

POSITIVE LOGITS

 string

0.49

 String

0.48

 Erişim

0.48

String

0.47

PropertyChanging

0.46

string

0.43

cobra

0.43

 seba

0.42

pretrained

0.42

Билгалдахарш

0.41

Activations Density 1.005%

prepositions

string

No Comments

No Known Activations