INDEX

Explanations

code or code snippets

oai_token-act-pair · gemini-2.0-flash

Code

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

ьаж

-0.64

 незавершена

-0.55

helves

-0.54

IMPORTED

-0.54

 يتيمه

-0.50

MemoryWarning

-0.43

helf

-0.43

VPB

-0.43

atius

-0.42

اليا

-0.42

POSITIVE LOGITS

 code

1.78

code

1.46

 codes

1.39

 Code

1.33

 código

1.32

 CODE

1.30

Code

1.27

代码

1.27

 코드

1.23

 software

1.20

Activations Density 3.830%

code or code snippets

Code

No Comments

No Known Activations

code or code snippets

Code

No Comments

No Known Activations