INDEX

Explanations

conditional statements or phrases where someone is speaking or wants to be heard

oai_token-act-pair · gemini-2.0-flash

listen

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

colage

-0.46

OfMonth

-0.45

Ess

-0.44

odas

-0.44

Expose

-0.44

siana

-0.43

 مربع

-0.43

ثة

-0.43

 tirada

-0.43

ggable

-0.42

POSITIVE LOGITS

 listen

1.38

 listening

1.34

ear

1.31

 ears

1.28

 listened

1.27

 listens

1.26

 LIST

1.25

 Listen

1.23

 Listening

1.18

 listener

1.16

Activations Density 0.566%

conditional statements or phrases where someone is speaking or wants to be heard

listen

No Comments

No Known Activations