INDEX

Explanations

sentences where something is important or difficult

oai_token-act-pair · gemini-2.0-flash

verb "to be"

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

 مصرى

-0.48

WillAppear

-0.47

 habet

-0.45

illant

-0.44

 entanto

-0.44

 antaranya

-0.43

 архивлан

-0.43

ydon

-0.42

dero

-0.42

лович

-0.42

POSITIVE LOGITS

enterOuterAlt

0.68

NameInMap

0.66

ArgsConstructor

0.63

Aiheesta

0.63

EndContext

0.63

 easier

0.60

MLLoader

0.60

ocellular

0.59

 ""],

0.57

 surla

0.57

Activations Density 0.497%

sentences where something is important or difficult

verb "to be"

No Comments

No Known Activations