INDEX

Explanations

questions of math and programming

oai_token-act-pair · gemini-2.0-flash

multiple

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

AnimationsModule

-0.76

PointerException

-0.60

 newOwner

-0.56

 Ring

-0.53

nościo

-0.53

---*/

-0.50

parsedMessage

-0.48

pecting

-0.48

Inflater

-0.47

 Caso

-0.46

POSITIVE LOGITS

 multiple

1.48

multiple

1.44

Multiple

1.38

 Multiple

1.37

 MULTIPLE

1.30

MULTIPLE

1.07

 multiples

0.97

 power

0.97

 múltip

0.92

power

0.90

Activations Density 6.181%

questions of math and programming

multiple

No Comments

No Known Activations