INDEX

Explanations

sequences of letters found in email addresses or names

oai_token-act-pair · gemini-2.0-flash

names, emails

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

tiqueta

-0.59

 EconPapers

-0.56

rítica

-0.54

irmer

-0.54

 respectively

-0.54

 paraître

-0.54

ParallelGroup

-0.53

muestra

-0.53

 successively

-0.52

assertArray

-0.52

POSITIVE LOGITS

ValueStyle

0.56

AnimationsModule

0.54

OGND

0.54

Clik

0.53

Hentet

0.52

DeleteBehavior

0.50

parsedMessage

0.48

StoryboardSegue

0.47

@"/

0.46

 nahilalakip

0.46

Activations Density 0.590%

sequences of letters found in email addresses or names

names, emails

No Comments

No Known Activations