INDEX

Explanations

a variety of numerical digits and nonstandard apostrophes

oai_token-act-pair · gemini-2.0-flash

Data snippets

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

<bos>

-0.62

saraba

-0.45

uxxxx

-0.43

XmlAccessType

-0.40

weg

-0.38

EventLoop

-0.38

Personensuche

-0.37

tangentMode

-0.36

Tikang

-0.36

 himo

-0.36

POSITIVE LOGITS

 becauſe

0.47

 Majefty

0.45

 Jefus

0.42

 himſelf

0.42

BaseAdapter

0.41

 fufficient

0.41

เอง

0.40

Espèce

0.40

rehensive

0.39

\,.

0.39

Activations Density 0.378%

a variety of numerical digits and nonstandard apostrophes

Data snippets

No Comments

No Known Activations