INDEX

Explanations

C-style code, related to defining bits and registers

oai_token-act-pair · gemini-2.0-flash

code snippets

np_token-act-pair-logits · gemini-2.0-flash

Code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ImageContext

-0.65

сылкі

-0.65

 Audiodateien

-0.59

 mergeFrom

-0.55

$_['

-0.54

 متحده

-0.54

 فريبيس

-0.53

λευτα

-0.53

 closure

-0.52

 parseFrom

-0.52

POSITIVE LOGITS

toHaveBeen

0.57

 sanitarios

0.56

+#+#

0.55

kuti

0.49

Nuorodos

0.48

NegativeButton

0.48

帖最后由

0.47

 bricola

0.45

 dégust

0.45

 savons

0.45

Activations Density 16.384%

C-style code, related to defining bits and registers

code snippets

Code

No Comments

No Known Activations