INDEX

Explanations

the verb "know" or cognates, often in the context of a person knowing something.

oai_token-act-pair · gemini-2.0-flash

know

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

 knowing

-0.87

KNOW

-0.87

 know

-0.86

know

-0.86

 Knows

-0.82

 Know

-0.82

Know

-0.82

 knows

-0.80

#+#

-0.79

 knowledge

-0.78

POSITIVE LOGITS

 what

0.48

ritis

0.46

het

0.45

how

0.43

the

0.43

rob

0.43

ambo

0.42

 prestation

0.42

 Buchung

0.42

Secondly

0.41

Activations Density 0.613%

the verb "know" or cognates, often in the context of a person knowing something.

know

No Comments

No Known Activations