INDEX

Explanations

sentences imploring the reader to do something

oai_token-act-pair · gemini-2.0-flash

Action words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 never

-0.57

never

-0.54

Never

-0.54

 pernah

-0.53

 Never

-0.52

 nigdy

-0.51

 aldri

-0.49

 Jangan

-0.49

 nunca

-0.47

Constantes

-0.45

POSITIVE LOGITS

get

0.91

 find

0.87

go

0.87

Get

0.79

 grab

0.76

 start

0.75

 prepare

0.75

richTextPanel

0.75

 Find

0.74

 enter

0.73

Activations Density 1.532%

sentences imploring the reader to do something

Action words

No Comments

No Known Activations