INDEX

Explanations

code snippets, particularly those that appear to be Perl

oai_token-act-pair · gemini-2.0-flash

code and scripting

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

MLLoader

-0.76

Enllaços

-0.62

alingen

-0.60

oa̍t

-0.60

protoimpl

-0.60

XmlAccessType

-0.59

 مصرى

-0.58

Personendaten

-0.58

HideFlags

-0.58

Diweddarwch

-0.57

POSITIVE LOGITS

 useRef

0.53

__(/*!

0.48

″]

0.48

 للمعارف

0.46

%;">

0.44

Get

0.43

Alors

0.43

 Alors

0.43

("%

0.43

daging

0.41

Activations Density 4.257%

code snippets, particularly those that appear to be Perl

code and scripting

No Comments

No Known Activations