INDEX

Explanations

code snippets followed by associated descriptions or names

oai_token-act-pair · gemini-2.0-flash

number

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

basicConfig

-0.64

ništvo

-0.63

 للمعارف

-0.61

 يتيمه

-0.60

RemindMe

-0.57

SizeF

-0.57

ConverterFactory

-0.57

///</

-0.56

Manbalar

-0.55

retario

-0.52

POSITIVE LOGITS

1.49

 number

1.45

 Number

1.44

number

1.33

Number

1.33

 Nummer

1.32

 NUMBER

1.30

\#

1.23

 nummer

1.23

№

1.19

Activations Density 1.808%

code snippets followed by associated descriptions or names

number

No Comments

No Known Activations