INDEX

Explanations

snippets of React Javascript code

oai_token-act-pair · gemini-2.0-flash

code, non-english

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

<bos>

-0.55

 McGrath

-0.47

atern

-0.46

bo

-0.45

$/,

-0.44

sto

-0.44

bus

-0.43

 Shouldn

-0.43

chi

-0.42

Gru

-0.42

POSITIVE LOGITS

 Paglinawan

0.79

rrggbb

0.73

IonicModule

0.71

pyplot

0.64

 considérons

0.64

aarrggbb

0.63

énario

0.60

gorit

0.58

ArrowToggle

0.57

Viitteet

0.57

Activations Density 0.453%

snippets of React Javascript code

code, non-english

No Comments

No Known Activations